Authors

This notebook is available to use, reproduce, and validate the author results for ClimateKG. Source notebook: authors.ipynb

It analyzes author contributions in the ClimateKG graph using the same workflow as the Report Structure notebook and the ER reference in The Rock.

ER-model baseline (The Rock)

Expected author-side model:

Authors are items with P1 -> Q3998 (Author class).
Authors should have a stable ClimateKG Author ID via P20.
Author contributions are modeled with P27 from Author to Chapter.
Chapters are items with P1 -> Q6 (Chapter class).

The queries below first check live graph conformance to that model, then summarize contributions using duplicate-safe counting by P20 (not by item URI).

Query UI: https://climatekg.tibwiki.io/query/

SPARQL endpoint: https://climatekg.tibwiki.io/query/proxy/sparql

Show code

import os
import pandas as pd
from SPARQLWrapper import JSON
from IPython.display import display, Markdown

from wikibase_auth import DEFAULT_SPARQL_ENDPOINT, DEFAULT_WIKIBASE_URL, build_sparql_client

os.environ.setdefault("CLIMATEKG_SPARQL_USERNAME", "ckg")
os.environ.setdefault("CLIMATEKG_SPARQL_PASSWORD", "fairdata")

SPARQL_ENDPOINT = os.getenv("CLIMATEKG_SPARQL_ENDPOINT", DEFAULT_SPARQL_ENDPOINT)
WIKIBASE_URL = os.getenv("CLIMATEKG_WIKIBASE_URL", DEFAULT_WIKIBASE_URL)

ENTITY_NS = f"{WIKIBASE_URL.rstrip('/')}/entity/"
PROPERTY_NS = f"{WIKIBASE_URL.rstrip('/')}/prop/direct/"

print(f"Endpoint: {SPARQL_ENDPOINT}")
print(f"Entity namespace: {ENTITY_NS}")
print(f"Property namespace: {PROPERTY_NS}")
print("Libraries imported successfully")

'ckg'

'fairdata'

Endpoint: https://climatekg.tibwiki.io/query/proxy/sparql
Entity namespace: https://climatekg.tibwiki.io/entity/
Property namespace: https://climatekg.tibwiki.io/prop/direct/
Libraries imported successfully

Show code

author_query = f'''
PREFIX wd: <{ENTITY_NS}>
PREFIX wdt: <{PROPERTY_NS}>
PREFIX rdfs: <http://www.w3.org/2000/01/rdf-schema#>

SELECT ?author ?authorLabel ?authorId ?chapter ?chapterLabel
WHERE {{
  ?author wdt:P1 wd:Q3998 ;
          wdt:P20 ?authorId ;
          wdt:P27 ?chapter .
  ?chapter wdt:P1 wd:Q6 .

  OPTIONAL {{ ?author rdfs:label ?authorLabel . FILTER(LANG(?authorLabel) = "en") }}
  OPTIONAL {{ ?chapter rdfs:label ?chapterLabel . FILTER(LANG(?chapterLabel) = "en") }}
}}
ORDER BY ?authorLabel ?chapterLabel
'''

sparql = build_sparql_client(SPARQL_ENDPOINT)
sparql.setQuery(author_query)
sparql.setReturnFormat(JSON)
author_results = sparql.query().convert()
author_rows = author_results.get("results", {}).get("bindings", [])

authors_df = pd.DataFrame([{k: v["value"] for k, v in row.items()} for row in author_rows])

if authors_df.empty:
    display(Markdown("No author-chapter rows returned from live graph."))
else:
    authors_df["authorId"] = authors_df["authorId"].astype(str)
    authors_df["authorQID"] = authors_df["author"].astype(str).str.rsplit("/", n=1).str[-1]
    dedup_authors = authors_df.drop_duplicates(subset=["authorId"])
    chapter_counts = (
        authors_df.groupby("authorId", as_index=False)
        .agg(
            authorQID=("authorQID", "first"),
            authorLabel=("authorLabel", "first"),
            chapter_count=("chapter", "nunique"),
        )
        .sort_values(["chapter_count", "authorLabel"], ascending=[False, True])
    )

    print(f"Author-chapter rows returned: {len(authors_df)}")
    print(f"Distinct authors by P20: {dedup_authors['authorId'].nunique()}")
    print(f"Distinct chapter URIs linked from P27: {authors_df['chapter'].nunique()}")

    display(Markdown("### Sample author-chapter links"))
    display(authors_df[["authorQID", "authorLabel", "authorId", "chapterLabel"]].head(20))

    display(Markdown("### Top authors by unique chapter contributions"))
    display(chapter_counts.head(20))

def run_count(query_text):
    sparql.setQuery(query_text)
    sparql.setReturnFormat(JSON)
    result = sparql.query().convert()
    row = result.get("results", {}).get("bindings", [{}])[0]
    if not row:
        return 0
    first_key = next(iter(row.keys()))
    return int(row[first_key]["value"])

def run_table(query_text):
    sparql.setQuery(query_text)
    sparql.setReturnFormat(JSON)
    result = sparql.query().convert()
    rows = result.get("results", {}).get("bindings", [])
    return pd.DataFrame([{k: v["value"] for k, v in row.items()} for row in rows])

conformance_metrics = [
    (
        "Author items (Q3998)",
        f'''
        PREFIX wd: <{ENTITY_NS}>
        PREFIX wdt: <{PROPERTY_NS}>
        SELECT (COUNT(DISTINCT ?item) AS ?count) WHERE {{
          ?item wdt:P1 wd:Q3998 .
        }}
        '''
    ),
    (
        "Distinct ClimateKG Author IDs (P20)",
        f'''
        PREFIX wd: <{ENTITY_NS}>
        PREFIX wdt: <{PROPERTY_NS}>
        SELECT (COUNT(DISTINCT ?authorId) AS ?count) WHERE {{
          ?item wdt:P1 wd:Q3998 ; wdt:P20 ?authorId .
        }}
        '''
    ),
    (
        "Chapter items (Q6)",
        f'''
        PREFIX wd: <{ENTITY_NS}>
        PREFIX wdt: <{PROPERTY_NS}>
        SELECT (COUNT(DISTINCT ?chapter) AS ?count) WHERE {{
          ?chapter wdt:P1 wd:Q6 .
        }}
        '''
    ),
    (
        "Distinct P20 IDs with P27->Q6 links",
        f'''
        PREFIX wd: <{ENTITY_NS}>
        PREFIX wdt: <{PROPERTY_NS}>
        SELECT (COUNT(DISTINCT ?authorId) AS ?count) WHERE {{
          ?author wdt:P1 wd:Q3998 ;
                  wdt:P20 ?authorId ;
                  wdt:P27 ?chapter .
          ?chapter wdt:P1 wd:Q6 .
        }}
        '''
    ),
]

metrics_rows = []
for metric_name, metric_query in conformance_metrics:
    metrics_rows.append({
        "metric": metric_name,
        "value": run_count(metric_query),
    })

conformance_df = pd.DataFrame(metrics_rows)
display(Markdown("### ER-model conformance snapshot"))
display(conformance_df)

validation_queries = {
    "Authors missing P20": f'''
        PREFIX wd: <{ENTITY_NS}>
        PREFIX wdt: <{PROPERTY_NS}>
        PREFIX rdfs: <http://www.w3.org/2000/01/rdf-schema#>
        SELECT ?author ?authorLabel
        WHERE {{
          ?author wdt:P1 wd:Q3998 .
          FILTER NOT EXISTS {{ ?author wdt:P20 ?authorId }}
          OPTIONAL {{ ?author rdfs:label ?authorLabel . FILTER(LANG(?authorLabel) = "en") }}
        }}
        ORDER BY ?author
    ''',
    "Authors missing any P27 contribution": f'''
        PREFIX wd: <{ENTITY_NS}>
        PREFIX wdt: <{PROPERTY_NS}>
        PREFIX rdfs: <http://www.w3.org/2000/01/rdf-schema#>
        SELECT ?author ?authorLabel ?authorId
        WHERE {{
          ?author wdt:P1 wd:Q3998 ; wdt:P20 ?authorId .
          FILTER NOT EXISTS {{ ?author wdt:P27 ?target }}
          OPTIONAL {{ ?author rdfs:label ?authorLabel . FILTER(LANG(?authorLabel) = "en") }}
        }}
        ORDER BY ?authorId
    ''',
    "Authors with P27 target not typed Q6": f'''
        PREFIX wd: <{ENTITY_NS}>
        PREFIX wdt: <{PROPERTY_NS}>
        PREFIX rdfs: <http://www.w3.org/2000/01/rdf-schema#>
        SELECT ?author ?authorLabel ?authorId ?target ?targetLabel ?targetClass ?targetClassLabel
        WHERE {{
          ?author wdt:P1 wd:Q3998 ; wdt:P20 ?authorId ; wdt:P27 ?target .
          FILTER NOT EXISTS {{ ?target wdt:P1 wd:Q6 }}
          OPTIONAL {{ ?author rdfs:label ?authorLabel . FILTER(LANG(?authorLabel) = "en") }}
          OPTIONAL {{ ?target rdfs:label ?targetLabel . FILTER(LANG(?targetLabel) = "en") }}
          OPTIONAL {{ ?target wdt:P1 ?targetClass . OPTIONAL {{ ?targetClass rdfs:label ?targetClassLabel . FILTER(LANG(?targetClassLabel) = "en") }} }}
        }}
        ORDER BY ?authorId ?target
    ''',
    "Duplicate P20 IDs assigned to multiple author items": f'''
        PREFIX wd: <{ENTITY_NS}>
        PREFIX wdt: <{PROPERTY_NS}>
        SELECT ?authorId (COUNT(DISTINCT ?author) AS ?authorItems)
        WHERE {{
          ?author wdt:P1 wd:Q3998 ; wdt:P20 ?authorId .
        }}
        GROUP BY ?authorId
        HAVING (COUNT(DISTINCT ?author) > 1)
        ORDER BY DESC(?authorItems) ?authorId
    ''',
}

display(Markdown("### Validation checks"))
validation_results = {}
for check_name, check_query in validation_queries.items():
    check_df = run_table(check_query)
    validation_results[check_name] = check_df
    display(Markdown(f"#### {check_name}"))
    print(f"Rows: {len(check_df)}")
    if len(check_df) == 0:
        display(Markdown("No issues found."))
    else:
        for col in ["author", "target", "targetClass"]:
            if col in check_df.columns:
                qid_col = f"{col}QID"
                check_df[qid_col] = check_df[col].astype(str).str.rsplit("/", n=1).str[-1]
        display(check_df.head(30))

p27_class_profile = run_table(f'''
    PREFIX wd: <{ENTITY_NS}>
    PREFIX wdt: <{PROPERTY_NS}>
    PREFIX rdfs: <http://www.w3.org/2000/01/rdf-schema#>
    SELECT ?targetClass ?targetClassLabel (COUNT(DISTINCT ?author) AS ?authors) (COUNT(DISTINCT ?target) AS ?targets)
    WHERE {{
      ?author wdt:P1 wd:Q3998 ; wdt:P27 ?target .
      OPTIONAL {{ ?target wdt:P1 ?targetClass . OPTIONAL {{ ?targetClass rdfs:label ?targetClassLabel . FILTER(LANG(?targetClassLabel) = "en") }} }}
    }}
    GROUP BY ?targetClass ?targetClassLabel
    ORDER BY DESC(?authors) DESC(?targets)
''')

display(Markdown("#### P27 target class profile"))
display(p27_class_profile)

sample_author_qid = "Q4750"
statement_anatomy_query = f'''
    PREFIX wd: <{ENTITY_NS}>
    PREFIX p: <{WIKIBASE_URL.rstrip('/')}/prop/>
    PREFIX ps: <{WIKIBASE_URL.rstrip('/')}/prop/statement/>
    PREFIX pq: <{WIKIBASE_URL.rstrip('/')}/prop/qualifier/>
    PREFIX pr: <{WIKIBASE_URL.rstrip('/')}/prop/reference/>
    PREFIX prov: <http://www.w3.org/ns/prov#>
    PREFIX rdfs: <http://www.w3.org/2000/01/rdf-schema#>
    SELECT ?author ?authorLabel ?statement ?chapter ?chapterLabel ?role ?refSource ?refAccessDate
    WHERE {{
      BIND(wd:{sample_author_qid} AS ?author)
      ?author p:P27 ?statement .
      ?statement ps:P27 ?chapter .
      OPTIONAL {{ ?author rdfs:label ?authorLabel . FILTER(LANG(?authorLabel) = "en") }}
      OPTIONAL {{ ?chapter rdfs:label ?chapterLabel . FILTER(LANG(?chapterLabel) = "en") }}
      OPTIONAL {{ ?statement pq:P28 ?role . }}
      OPTIONAL {{
        ?statement prov:wasDerivedFrom ?refNode .
        OPTIONAL {{ ?refNode pr:P17 ?refSource . }}
        OPTIONAL {{ ?refNode pr:P18 ?refAccessDate . }}
      }}
    }}
    ORDER BY ?chapterLabel
'''

statement_df = run_table(statement_anatomy_query)
display(Markdown(f"#### Statement anatomy (sample Author {sample_author_qid})"))
if statement_df.empty:
    display(Markdown("No statement-level rows found for the sample author."))
else:
    statement_df["authorQID"] = statement_df["author"].astype(str).str.rsplit("/", n=1).str[-1]
    statement_df["chapterQID"] = statement_df["chapter"].astype(str).str.rsplit("/", n=1).str[-1]
    if "refAccessDate" in statement_df.columns:
        statement_df["refAccessDate"] = statement_df["refAccessDate"].astype(str).str.replace("T00:00:00Z", "", regex=False)
    cols = ["authorQID", "authorLabel", "chapterQID", "chapterLabel", "role", "refSource", "refAccessDate"]
    existing_cols = [c for c in cols if c in statement_df.columns]
    display(statement_df[existing_cols].drop_duplicates())

# Notebook note block: capture key validation findings in plain language.
missing_p20_count = len(validation_results.get("Authors missing P20", pd.DataFrame()))
missing_p27_count = len(validation_results.get("Authors missing any P27 contribution", pd.DataFrame()))
non_q6_df = validation_results.get("Authors with P27 target not typed Q6", pd.DataFrame())
duplicate_p20_count = len(validation_results.get("Duplicate P20 IDs assigned to multiple author items", pd.DataFrame()))

non_q6_count = len(non_q6_df)
if non_q6_count > 0 and "target" in non_q6_df.columns:
    non_q6_targets = sorted(non_q6_df["target"].dropna().astype(str).unique().tolist())
    non_q6_target_qids = sorted([uri.rsplit("/", 1)[-1] for uri in non_q6_targets])
else:
    non_q6_target_qids = []

notes_lines = [
    "### Validation notes",
    f"- Authors missing P20: {missing_p20_count}",
    f"- Authors missing P27 contributions: {missing_p27_count}",
    f"- Duplicate P20 IDs on multiple author items: {duplicate_p20_count}",
    f"- P27 links to non-Q6 targets: {non_q6_count}",
]

if non_q6_target_qids:
    notes_lines.append(f"- Non-Q6 target QIDs observed: {', '.join(non_q6_target_qids)}")

if not statement_df.empty:
    notes_lines.extend([
        "",
        f"Statement anatomy check ({sample_author_qid}) confirms claim-level metadata:",
        "- Main claim: P27 (contributed to chapter)",
        "- Author-side relationship role: P28 (role, e.g. Lead Author)",
        "- References: P17 (reference URL) and P18 (date accessed)",
    ])

notes_lines.extend([
    "",
    "Author property pattern observed from item-level inspection (Q4750):",
    "- Structural typing and relation properties: P1 (instance of), P27 (contributed to)",
    "- Identifier property: P20 (ClimateKG Author ID)",
    "- Biographic profile properties: P21 (last name), P22 (first name), P23 (gender), P24 (citizenship), P25 (country of residence), P26 (affiliation)",
])

display(Markdown("\n".join(notes_lines)))

Author-chapter rows returned: 1150
Distinct authors by P20: 921
Distinct chapter URIs linked from P27: 74

Sample author-chapter links

	authorQID	authorLabel	authorId	chapterLabel
0	Q4750	Adam Mohammed Sebbit	AU0752	Mitigation Pathways Compatible with Long-term ...
1	Q4833	Adelle Thomas	AU0835	Cities and Settlements by the Sea
2	Q4833	Adelle Thomas	AU0835	Impacts of 1.5°C Global Warming on Natural and...
3	Q4833	Adelle Thomas	AU0835	Key Risks across Sectors and Regions
4	Q4592	Aditi Mukherji	AU0594	High Mountain Areas
5	Q4592	Aditi Mukherji	AU0594	Longer Report
6	Q4592	Aditi Mukherji	AU0594	Summary for Policymakers
7	Q4592	Aditi Mukherji	AU0594	Water
8	Q4007	Adolf Acquaye	AU0009	Industry
9	Q4484	Adrian Leip	AU0486	Cross-sectoral Perspectives
10	Q4785	Adrian Spence	AU0787	Framing and context
11	Q4287	Adugna Gemeda	AU0289	Africa
12	Q4739	Agus Pratama Sari	AU0741	International Cooperation
13	Q4253	Aidan Farrell	AU0255	Food, Fibre and Other Ecosystem Products
14	Q4253	Aidan Farrell	AU0255	Tropical Forests
15	Q4774	Aimée Slangen	AU0776	Longer Report
16	Q4774	Aimée Slangen	AU0776	Ocean, Cryosphere and Sea Level Change
17	Q4774	Aimée Slangen	AU0776	Summary for Policymakers
18	Q4769	Ajay Kumar Singh	AU0771	Energy Systems
19	Q4441	Akio Kitoh	AU0443	Asia

Top authors by unique chapter contributions

	authorId	authorQID	authorLabel	chapter_count
282	AU0284	Q4282	Matthias Garschagen	5
588	AU0594	Q4592	Aditi Mukherji	4
3	AU0004	Q4002	Amjad Abdulla	4
696	AU0704	Q4702	Aromar Revi	4
341	AU0343	Q4341	Bronwyn Hayward	4
193	AU0195	Q4193	Fatima Denton	4
718	AU0727	Q4725	Joyashree Roy	4
108	AU0109	Q4107	Katherine Calvin	4
917	AU0929	Q4927	Zinta Zommers	4
825	AU0835	Q4833	Adelle Thomas	3
767	AU0776	Q4774	Aimée Slangen	3
719	AU0728	Q4726	Alexander Ruane	3
569	AU0575	Q4573	Alisher Mirzabaev	3
260	AU0262	Q4260	Andreas Fischlin	3
674	AU0682	Q4680	Anjal Prakash	3
809	AU0818	Q4816	Anna Amelia Sörensson	3
792	AU0801	Q4799	Avelino Gumersindo Suarez Rodriguez	3
210	AU0212	Q4210	Aïda Diongue-Niang	3
300	AU0302	Q4300	Bruce Glavovic	3
12	AU0013	Q4011	Carolina Adler	3

ER-model conformance snapshot

	metric	value
0	Author items (Q3998)	932
1	Distinct ClimateKG Author IDs (P20)	932
2	Chapter items (Q6)	87
3	Distinct P20 IDs with P27->Q6 links	921

Validation checks

Authors missing P20

Rows: 0

No issues found.

Authors missing any P27 contribution

Rows: 0

No issues found.

Authors with P27 target not typed Q6

Rows: 14

	author	authorLabel	authorId	target	authorQID	targetQID
0	https://climatekg.tibwiki.io/entity/Q4142	Francis Chiew	AU0144	https://climatekg.tibwiki.io/entity/Q128	Q4142	Q128
1	https://climatekg.tibwiki.io/entity/Q4165	Mark Costello	AU0167	https://climatekg.tibwiki.io/entity/Q128	Q4165	Q128
2	https://climatekg.tibwiki.io/entity/Q4345	Kevin Hennessy	AU0347	https://climatekg.tibwiki.io/entity/Q128	Q4345	Q128
3	https://climatekg.tibwiki.io/entity/Q4360	Ove Hoegh-Guldberg	AU0362	https://climatekg.tibwiki.io/entity/Q128	Q4360	Q128
4	https://climatekg.tibwiki.io/entity/Q4474	Nina Lansbury	AU0476	https://climatekg.tibwiki.io/entity/Q128	Q4474	Q128
5	https://climatekg.tibwiki.io/entity/Q4476	Judy Lawrence	AU0478	https://climatekg.tibwiki.io/entity/Q128	Q4476	Q128
6	https://climatekg.tibwiki.io/entity/Q4518	Brendan Mackey	AU0520	https://climatekg.tibwiki.io/entity/Q128	Q4518	Q128
7	https://climatekg.tibwiki.io/entity/Q4620	Uday Bhaskar Nidumolu	AU0622	https://climatekg.tibwiki.io/entity/Q128	Q4620	Q128
8	https://climatekg.tibwiki.io/entity/Q4658	Gretta Pecl	AU0660	https://climatekg.tibwiki.io/entity/Q128	Q4658	Q128
9	https://climatekg.tibwiki.io/entity/Q4707	Lauren Rickards	AU0709	https://climatekg.tibwiki.io/entity/Q128	Q4707	Q128
10	https://climatekg.tibwiki.io/entity/Q4825	Nigel Tapper	AU0827	https://climatekg.tibwiki.io/entity/Q128	Q4825	Q128
11	https://climatekg.tibwiki.io/entity/Q4894	Alistair Woodward	AU0896	https://climatekg.tibwiki.io/entity/Q128	Q4894	Q128
12	https://climatekg.tibwiki.io/entity/Q4896	David Wratt	AU0898	https://climatekg.tibwiki.io/entity/Q128	Q4896	Q128
13	https://climatekg.tibwiki.io/entity/Q4897	Anita Wreford	AU0899	https://climatekg.tibwiki.io/entity/Q128	Q4897	Q128

Duplicate P20 IDs assigned to multiple author items

Rows: 0

No issues found.

P27 target class profile

	targetClass	targetClassLabel	authors	targets
0	https://climatekg.tibwiki.io/entity/Q6	Chapter	921	74
1	https://climatekg.tibwiki.io/entity/Q5	Text Division	19	1
2	NaN	NaN	14	1

Statement anatomy (sample Author Q4750)

	authorQID	authorLabel	chapterQID	chapterLabel	role	refSource	refAccessDate
0	Q4750	Adam Mohammed Sebbit	Q158	Mitigation Pathways Compatible with Long-term ...	Lead Author	https://apps.ipcc.ch/report/authors/	2026-03-18

Validation notes

Authors missing P20: 0
Authors missing P27 contributions: 0
Duplicate P20 IDs on multiple author items: 0
P27 links to non-Q6 targets: 14
Non-Q6 target QIDs observed: Q128

Statement anatomy check (Q4750) confirms claim-level metadata: - Main claim: P27 (contributed to chapter) - Author-side relationship role: P28 (role, e.g. Lead Author) - References: P17 (reference URL) and P18 (date accessed)

Author property pattern observed from item-level inspection (Q4750): - Structural typing and relation properties: P1 (instance of), P27 (contributed to) - Identifier property: P20 (ClimateKG Author ID) - Biographic profile properties: P21 (last name), P22 (first name), P23 (gender), P24 (citizenship), P25 (country of residence), P26 (affiliation)

Interpretation

This notebook now follows the same structure used in Report Structure:

Start from the ER baseline in The Rock (Q3998 Author, Q6 Chapter, P20 author ID, P27 contributed-to relation).
Query the live graph for author-chapter links.
Report duplicate-safe metrics by deduplicating authors on P20.
Run validation checks to flag modeling exceptions.

The key lesson from the structure notebook also applies here: we should not infer completeness from raw item counts alone. Where duplicate imports exist, author-level counts must be grounded on distinct P20 values, while relationships (P27) are validated against chapters typed as Q6.

Statement anatomy

The validation cell now includes a statement-level anatomy view for sample author Q4750, showing how one P27 contribution is represented with:

Main claim value (P27 -> chapter item)
Author-side relationship role (P28 role, e.g. Lead Author)
References (P17 reference URL and P18 date accessed)

This helps verify that the graph carries provenance at claim level, not only at item level.

Author property usage learned from item inspection

From the concrete author item Q4750 and the broader validation checks, the current Author pattern uses the following fields.

Property	Label / Purpose	Role in Author model
`P1`	Instance of	Class typing (`Q3998` Author)
`P20`	ClimateKG Author ID	Stable author identifier used for deduplication
`P27`	contributed to chapter	Link from Author to contribution target (expected class `Q6` Chapter)
`P28`	author role on chapter contribution	Author-side contribution role qualifier used on the `P27` statement
`P21`	last name	Biographic/profile attribute
`P22`	first name	Biographic/profile attribute
`P23`	gender	Biographic/profile attribute
`P24`	citizenship	Biographic/profile attribute
`P25`	country of residence	Biographic/profile attribute
`P26`	affiliation	Biographic/profile attribute

Wikibase provenance and reference-related fields

These fields are important for source tracking and auditability when present in the graph (either on author records or related records used in the pipeline).

Property	Label / Purpose	Provenance use
`P6`	Source	Original source URL for imported data
`P17`	Reference URL	Reference URL attached to a statement reference
`P18`	date accessed	Alternate/duplicate access-date field seen in model
`P19`	source version	Captures source version metadata
`P5`	Wiki	Link to corresponding wiki page/resource
`P7`	PDF	Link to source PDF resource when relevant

This provides a practical validation template: every Author should have P1, P20, and at least one P27, P27 targets should normally resolve to class Q6 Chapter, and provenance fields should be populated where available for traceability.

Bibliographic questions

From the GitHub issue: https://github.com/TIBHannover/ClimateKG-Data-Bench/issues/1

How many distinct authors contributed to each of the 7 reports?
Which countries of residence are most represented among AR6 authors, and how does this differ between WGI, WGII and WGIII?
What is the share of female authors per working group report, and which chapters have the lowest female representation?
Which authors contributed to chapters in more than one working group report?
Which two authors have co-authored the most chapters together?
Which institutions have the most authors across AR6?

Question 1

How many distinct authors contributed to each of the 7 reports? This cell uses the live SPARQL endpoint and counts distinct author IDs (P20) for each report.

Show code

query = f'''
PREFIX wd: <{ENTITY_NS}>
PREFIX wdt: <{PROPERTY_NS}>
PREFIX rdfs: <http://www.w3.org/2000/01/rdf-schema#>
SELECT ?report ?reportLabel (COUNT(DISTINCT ?authorId) AS ?distinctAuthors)
WHERE {{
  ?author wdt:P1 wd:Q3998 ;
          wdt:P20 ?authorId ;
          wdt:P27 ?chapter .
  ?chapter wdt:P3+ ?report .
  ?report wdt:P1 wd:Q4 ;
          rdfs:label ?reportLabel .
  FILTER(LANG(?reportLabel) = "en")
}}
GROUP BY ?report ?reportLabel
ORDER BY ?reportLabel
'''

display(Markdown("**SPARQL query (copy/paste into ClimateKG Query UI: https://climatekg.tibwiki.io/query/)**"))
display(Markdown("```sparql\n" + query + "\n```"))
report_df = run_table(query).sort_values("reportLabel").reset_index(drop=True)
report_df["reportQID"] = report_df["report"].astype(str).str.rsplit("/", n=1).str[-1]
display(report_df[["reportQID", "reportLabel", "distinctAuthors"]])

SPARQL query (copy/paste into ClimateKG Query UI: https://climatekg.tibwiki.io/query/)


PREFIX wd: <https://climatekg.tibwiki.io/entity/>
PREFIX wdt: <https://climatekg.tibwiki.io/prop/direct/>
PREFIX rdfs: <http://www.w3.org/2000/01/rdf-schema#>
SELECT ?report ?reportLabel (COUNT(DISTINCT ?authorId) AS ?distinctAuthors)
WHERE {
  ?author wdt:P1 wd:Q3998 ;
          wdt:P20 ?authorId ;
          wdt:P27 ?chapter .
  ?chapter wdt:P3+ ?report .
  ?report wdt:P1 wd:Q4 ;
          rdfs:label ?reportLabel .
  FILTER(LANG(?reportLabel) = "en")
}
GROUP BY ?report ?reportLabel
ORDER BY ?reportLabel

	reportQID	reportLabel	distinctAuthors
0	Q189	Climate Change 2023: Synthesis Report. Contrib...	30
1	Q35	Special Report: Climate Change and Land	107
2	Q10	Special Report: Global Warming of 1.5°C	91
3	Q57	Special Report: The Ocean and Cryosphere in a ...	103
4	Q77	Working Group I: Climate Change 2021 – The Phy...	234
5	Q106	Working Group II: Climate Change 2022 – Impact...	257
6	Q150	Working Group III: Climate Change 2022 – Mitig...	239

Question 2

Which countries of residence are most represented among AR6 authors, and how does this differ between WGI, WGII and WGIII? This cell uses the live SPARQL endpoint and counts distinct authors (P20) by country (P25).

Show code

query = f'''
PREFIX wd: <{ENTITY_NS}>
PREFIX wdt: <{PROPERTY_NS}>
PREFIX rdfs: <http://www.w3.org/2000/01/rdf-schema#>
SELECT ?workingGroupLabel ?country (COUNT(DISTINCT ?authorId) AS ?authors)
WHERE {{
  ?author wdt:P1 wd:Q3998 ;
          wdt:P20 ?authorId ;
          wdt:P25 ?country ;
          wdt:P27 ?chapter .
  ?chapter wdt:P3+ ?report .
  ?report wdt:P1 wd:Q4 ;
          rdfs:label ?reportLabel .
  FILTER(LANG(?reportLabel) = "en")
  BIND(IF(CONTAINS(?reportLabel, "Working Group I:"), "Working Group I",
       IF(CONTAINS(?reportLabel, "Working Group II:"), "Working Group II",
       IF(CONTAINS(?reportLabel, "Working Group III:"), "Working Group III", "Other"))) AS ?workingGroupLabel)
  FILTER(?workingGroupLabel != "Other")
}}
GROUP BY ?workingGroupLabel ?country
ORDER BY ?workingGroupLabel DESC(?authors) ?country
'''

display(Markdown("**SPARQL query (copy/paste into ClimateKG Query UI: https://climatekg.tibwiki.io/query/)**"))
display(Markdown("```sparql\n" + query + "\n```"))
country_df = run_table(query)
country_top = country_df.sort_values(["workingGroupLabel", "authors", "country"], ascending=[True, False, True]).groupby("workingGroupLabel", as_index=False).head(10)
display(country_top[["workingGroupLabel", "country", "authors"]])

SPARQL query (copy/paste into ClimateKG Query UI: https://climatekg.tibwiki.io/query/)


PREFIX wd: <https://climatekg.tibwiki.io/entity/>
PREFIX wdt: <https://climatekg.tibwiki.io/prop/direct/>
PREFIX rdfs: <http://www.w3.org/2000/01/rdf-schema#>
SELECT ?workingGroupLabel ?country (COUNT(DISTINCT ?authorId) AS ?authors)
WHERE {
  ?author wdt:P1 wd:Q3998 ;
          wdt:P20 ?authorId ;
          wdt:P25 ?country ;
          wdt:P27 ?chapter .
  ?chapter wdt:P3+ ?report .
  ?report wdt:P1 wd:Q4 ;
          rdfs:label ?reportLabel .
  FILTER(LANG(?reportLabel) = "en")
  BIND(IF(CONTAINS(?reportLabel, "Working Group I:"), "Working Group I",
       IF(CONTAINS(?reportLabel, "Working Group II:"), "Working Group II",
       IF(CONTAINS(?reportLabel, "Working Group III:"), "Working Group III", "Other"))) AS ?workingGroupLabel)
  FILTER(?workingGroupLabel != "Other")
}
GROUP BY ?workingGroupLabel ?country
ORDER BY ?workingGroupLabel DESC(?authors) ?country

	workingGroupLabel	country	authors
6	Working Group I	Canada	8
7	Working Group I	Germany	8
8	Working Group I	Norway	7
9	Working Group I	Brazil	6
10	Working Group I	India	6
11	Working Group I	Italy	6
12	Working Group I	Argentina	5
13	Working Group I	Netherlands	5
14	Working Group I	Republic of Korea	5
15	Working Group I	South Africa	5
71	Working Group II	Canada	9
72	Working Group II	Mexico	8
73	Working Group II	South Africa	8
74	Working Group II	France	7
75	Working Group II	Norway	7
76	Working Group II	Switzerland	7
77	Working Group II	Netherlands	6
78	Working Group II	Brazil	5
79	Working Group II	Spain	5
80	Working Group II	Tanzania	5
133	Working Group III	Brazil	9
134	Working Group III	Austria	7
135	Working Group III	France	7
136	Working Group III	Italy	7
137	Working Group III	Canada	6
138	Working Group III	Netherlands	6
139	Working Group III	Norway	6
140	Working Group III	Argentina	4
141	Working Group III	Denmark	4
142	Working Group III	Spain	4

Question 3

What is the share of female authors per working group report, and which chapters have the lowest female representation? This cell uses the live SPARQL endpoint and deduplicates authors by P20 before calculating shares.

Show code

query = f'''
PREFIX wd: <{ENTITY_NS}>
PREFIX wdt: <{PROPERTY_NS}>
PREFIX rdfs: <http://www.w3.org/2000/01/rdf-schema#>
SELECT ?workingGroupLabel (COUNT(DISTINCT ?authorId) AS ?authors) (SUM(?isFemale) AS ?femaleAuthors) (SUM(?isMale) AS ?maleAuthors)
WHERE {{
  {{
    SELECT DISTINCT ?workingGroupLabel ?authorId ?gender
    WHERE {{
      ?author wdt:P1 wd:Q3998 ;
              wdt:P20 ?authorId ;
              wdt:P23 ?gender ;
              wdt:P27 ?chapter .
      ?chapter wdt:P3+ ?report .
      ?report wdt:P1 wd:Q4 ;
              rdfs:label ?reportLabel .
      FILTER(LANG(?reportLabel) = "en")
      BIND(IF(CONTAINS(?reportLabel, "Working Group I:"), "Working Group I",
           IF(CONTAINS(?reportLabel, "Working Group II:"), "Working Group II",
           IF(CONTAINS(?reportLabel, "Working Group III:"), "Working Group III", "Other"))) AS ?workingGroupLabel)
      FILTER(?workingGroupLabel != "Other")
    }}
  }}
  BIND(IF(LCASE(STR(?gender)) = "f", 1, 0) AS ?isFemale)
  BIND(IF(LCASE(STR(?gender)) = "m", 1, 0) AS ?isMale)
}}
GROUP BY ?workingGroupLabel
ORDER BY ?workingGroupLabel
'''

display(Markdown("**SPARQL query (copy/paste into ClimateKG Query UI: https://climatekg.tibwiki.io/query/)**"))
display(Markdown("```sparql\n" + query + "\n```"))
female_report_df = run_table(query)
female_report_df["femaleSharePct"] = (female_report_df["femaleAuthors"].astype(float) / female_report_df["authors"].astype(float) * 100).round(1)
female_report_df["maleSharePct"] = (female_report_df["maleAuthors"].astype(float) / female_report_df["authors"].astype(float) * 100).round(1)
display(female_report_df[["workingGroupLabel", "authors", "femaleAuthors", "maleAuthors", "femaleSharePct", "maleSharePct"]])

chapter_query = f'''
PREFIX wd: <{ENTITY_NS}>
PREFIX wdt: <{PROPERTY_NS}>
PREFIX rdfs: <http://www.w3.org/2000/01/rdf-schema#>
SELECT ?workingGroupLabel ?chapter ?chapterLabel (COUNT(DISTINCT ?authorId) AS ?authors) (SUM(?isFemale) AS ?femaleAuthors) (SUM(?isMale) AS ?maleAuthors)
WHERE {{
  {{
    SELECT DISTINCT ?workingGroupLabel ?chapter ?chapterLabel ?authorId ?gender
    WHERE {{
      ?author wdt:P1 wd:Q3998 ;
              wdt:P20 ?authorId ;
              wdt:P23 ?gender ;
              wdt:P27 ?chapter .
      ?chapter wdt:P1 wd:Q6 ;
               rdfs:label ?chapterLabel .
      FILTER(LANG(?chapterLabel) = "en")
      ?chapter wdt:P3+ ?report .
      ?report wdt:P1 wd:Q4 ;
              rdfs:label ?reportLabel .
      FILTER(LANG(?reportLabel) = "en")
      BIND(IF(CONTAINS(?reportLabel, "Working Group I:"), "Working Group I",
           IF(CONTAINS(?reportLabel, "Working Group II:"), "Working Group II",
           IF(CONTAINS(?reportLabel, "Working Group III:"), "Working Group III", "Other"))) AS ?workingGroupLabel)
      FILTER(?workingGroupLabel != "Other")
    }}
  }}
  BIND(IF(LCASE(STR(?gender)) = "f", 1, 0) AS ?isFemale)
  BIND(IF(LCASE(STR(?gender)) = "m", 1, 0) AS ?isMale)
}}
GROUP BY ?workingGroupLabel ?chapter ?chapterLabel
ORDER BY ASC((?femaleAuthors / ?authors)) ?workingGroupLabel ?chapterLabel
'''

display(Markdown("**SPARQL query (copy/paste into ClimateKG Query UI: https://climatekg.tibwiki.io/query/)**"))
display(Markdown("```sparql\n" + chapter_query + "\n```"))
female_chapter_df = run_table(chapter_query)
female_chapter_df["femaleSharePct"] = (female_chapter_df["femaleAuthors"].astype(float) / female_chapter_df["authors"].astype(float) * 100).round(1)
female_chapter_df["maleSharePct"] = (female_chapter_df["maleAuthors"].astype(float) / female_chapter_df["authors"].astype(float) * 100).round(1)
lowest_female = female_chapter_df.sort_values(["femaleSharePct", "workingGroupLabel", "chapterLabel"], ascending=[True, True, True]).head(10)
display(lowest_female[["workingGroupLabel", "chapterLabel", "authors", "femaleAuthors", "maleAuthors", "femaleSharePct", "maleSharePct"]])

SPARQL query (copy/paste into ClimateKG Query UI: https://climatekg.tibwiki.io/query/)


PREFIX wd: <https://climatekg.tibwiki.io/entity/>
PREFIX wdt: <https://climatekg.tibwiki.io/prop/direct/>
PREFIX rdfs: <http://www.w3.org/2000/01/rdf-schema#>
SELECT ?workingGroupLabel (COUNT(DISTINCT ?authorId) AS ?authors) (SUM(?isFemale) AS ?femaleAuthors) (SUM(?isMale) AS ?maleAuthors)
WHERE {
  {
    SELECT DISTINCT ?workingGroupLabel ?authorId ?gender
    WHERE {
      ?author wdt:P1 wd:Q3998 ;
              wdt:P20 ?authorId ;
              wdt:P23 ?gender ;
              wdt:P27 ?chapter .
      ?chapter wdt:P3+ ?report .
      ?report wdt:P1 wd:Q4 ;
              rdfs:label ?reportLabel .
      FILTER(LANG(?reportLabel) = "en")
      BIND(IF(CONTAINS(?reportLabel, "Working Group I:"), "Working Group I",
           IF(CONTAINS(?reportLabel, "Working Group II:"), "Working Group II",
           IF(CONTAINS(?reportLabel, "Working Group III:"), "Working Group III", "Other"))) AS ?workingGroupLabel)
      FILTER(?workingGroupLabel != "Other")
    }
  }
  BIND(IF(LCASE(STR(?gender)) = "f", 1, 0) AS ?isFemale)
  BIND(IF(LCASE(STR(?gender)) = "m", 1, 0) AS ?isMale)
}
GROUP BY ?workingGroupLabel
ORDER BY ?workingGroupLabel

	workingGroupLabel	authors	femaleAuthors	maleAuthors	femaleSharePct	maleSharePct
0	Working Group I	234	66	168	28.2	71.8
1	Working Group II	257	106	151	41.2	58.8
2	Working Group III	239	77	162	32.2	67.8

SPARQL query (copy/paste into ClimateKG Query UI: https://climatekg.tibwiki.io/query/)


PREFIX wd: <https://climatekg.tibwiki.io/entity/>
PREFIX wdt: <https://climatekg.tibwiki.io/prop/direct/>
PREFIX rdfs: <http://www.w3.org/2000/01/rdf-schema#>
SELECT ?workingGroupLabel ?chapter ?chapterLabel (COUNT(DISTINCT ?authorId) AS ?authors) (SUM(?isFemale) AS ?femaleAuthors) (SUM(?isMale) AS ?maleAuthors)
WHERE {
  {
    SELECT DISTINCT ?workingGroupLabel ?chapter ?chapterLabel ?authorId ?gender
    WHERE {
      ?author wdt:P1 wd:Q3998 ;
              wdt:P20 ?authorId ;
              wdt:P23 ?gender ;
              wdt:P27 ?chapter .
      ?chapter wdt:P1 wd:Q6 ;
               rdfs:label ?chapterLabel .
      FILTER(LANG(?chapterLabel) = "en")
      ?chapter wdt:P3+ ?report .
      ?report wdt:P1 wd:Q4 ;
              rdfs:label ?reportLabel .
      FILTER(LANG(?reportLabel) = "en")
      BIND(IF(CONTAINS(?reportLabel, "Working Group I:"), "Working Group I",
           IF(CONTAINS(?reportLabel, "Working Group II:"), "Working Group II",
           IF(CONTAINS(?reportLabel, "Working Group III:"), "Working Group III", "Other"))) AS ?workingGroupLabel)
      FILTER(?workingGroupLabel != "Other")
    }
  }
  BIND(IF(LCASE(STR(?gender)) = "f", 1, 0) AS ?isFemale)
  BIND(IF(LCASE(STR(?gender)) = "m", 1, 0) AS ?isMale)
}
GROUP BY ?workingGroupLabel ?chapter ?chapterLabel
ORDER BY ASC((?femaleAuthors / ?authors)) ?workingGroupLabel ?chapterLabel

	workingGroupLabel	chapterLabel	authors	femaleAuthors	maleAuthors	femaleSharePct	maleSharePct
0	Working Group II	Tropical Forests	8	1	7	12.5	87.5
1	Working Group I	The Earth’s Energy Budget, Climate Feedbacks a...	15	2	13	13.3	86.7
2	Working Group III	Cross-sectoral Perspectives	13	2	11	15.4	84.6
3	Working Group III	Industry	11	2	9	18.2	81.8
4	Working Group I	Global Carbon and Other Biogeochemical Cycles ...	19	4	15	21.1	78.9
5	Working Group I	Linking Global to Regional Climate Change	19	4	15	21.1	78.9
6	Working Group II	Point of Departure and Key Concepts	14	3	11	21.4	78.6
7	Working Group III	Energy Systems	14	3	11	21.4	78.6
8	Working Group I	Climate Change Information for Regional Impact...	18	4	14	22.2	77.8
9	Working Group I	Future Global Climate: Scenario-based Projecti...	18	4	14	22.2	77.8

Question 4

Which authors contributed to chapters in more than one working group report? This cell uses the live SPARQL endpoint and deduplicates authors by P20 before counting working groups.

Show code

query = f'''
PREFIX wd: <{ENTITY_NS}>
PREFIX wdt: <{PROPERTY_NS}>
PREFIX rdfs: <http://www.w3.org/2000/01/rdf-schema#>
SELECT ?authorId ?authorLabel (COUNT(DISTINCT ?workingGroup) AS ?workingGroups) (GROUP_CONCAT(DISTINCT ?workingGroupLabel; separator=", ") AS ?groupLabels)
WHERE {{
  ?author wdt:P1 wd:Q3998 ;
          wdt:P20 ?authorId ;
          wdt:P27 ?chapter .
  OPTIONAL {{ ?author rdfs:label ?authorLabel . FILTER(LANG(?authorLabel) = "en") }}
  ?chapter wdt:P3+ ?report .
  ?report wdt:P1 wd:Q4 ;
          rdfs:label ?reportLabel .
  FILTER(LANG(?reportLabel) = "en")
  BIND(IF(CONTAINS(?reportLabel, "Working Group I:"), "WGI",
       IF(CONTAINS(?reportLabel, "Working Group II:"), "WGII",
       IF(CONTAINS(?reportLabel, "Working Group III:"), "WGIII", "Other"))) AS ?workingGroup)
  FILTER(?workingGroup != "Other")
  BIND(IF(?workingGroup = "WGI", "Working Group I", IF(?workingGroup = "WGII", "Working Group II", "Working Group III")) AS ?workingGroupLabel)
}}
GROUP BY ?authorId ?authorLabel
HAVING (COUNT(DISTINCT ?workingGroup) > 1)
ORDER BY DESC(?workingGroups) ?authorLabel
'''

display(Markdown("**SPARQL query (copy/paste into ClimateKG Query UI: https://climatekg.tibwiki.io/query/)**"))
display(Markdown("```sparql\n" + query + "\n```"))
multi_wg_df = run_table(query)
display(multi_wg_df[["authorLabel", "authorId", "workingGroups", "groupLabels"]])

SPARQL query (copy/paste into ClimateKG Query UI: https://climatekg.tibwiki.io/query/)


PREFIX wd: <https://climatekg.tibwiki.io/entity/>
PREFIX wdt: <https://climatekg.tibwiki.io/prop/direct/>
PREFIX rdfs: <http://www.w3.org/2000/01/rdf-schema#>
SELECT ?authorId ?authorLabel (COUNT(DISTINCT ?workingGroup) AS ?workingGroups) (GROUP_CONCAT(DISTINCT ?workingGroupLabel; separator=", ") AS ?groupLabels)
WHERE {
  ?author wdt:P1 wd:Q3998 ;
          wdt:P20 ?authorId ;
          wdt:P27 ?chapter .
  OPTIONAL { ?author rdfs:label ?authorLabel . FILTER(LANG(?authorLabel) = "en") }
  ?chapter wdt:P3+ ?report .
  ?report wdt:P1 wd:Q4 ;
          rdfs:label ?reportLabel .
  FILTER(LANG(?reportLabel) = "en")
  BIND(IF(CONTAINS(?reportLabel, "Working Group I:"), "WGI",
       IF(CONTAINS(?reportLabel, "Working Group II:"), "WGII",
       IF(CONTAINS(?reportLabel, "Working Group III:"), "WGIII", "Other"))) AS ?workingGroup)
  FILTER(?workingGroup != "Other")
  BIND(IF(?workingGroup = "WGI", "Working Group I", IF(?workingGroup = "WGII", "Working Group II", "Working Group III")) AS ?workingGroupLabel)
}
GROUP BY ?authorId ?authorLabel
HAVING (COUNT(DISTINCT ?workingGroup) > 1)
ORDER BY DESC(?workingGroups) ?authorLabel

	authorLabel	authorId	workingGroups	groupLabels
0	Linda Mearns	AU0554	2	Working Group II, Working Group I
1	Patricia Romero Lankao	AU0721	2	Working Group III, Working Group II

Question 5

Which two authors have co-authored the most chapters together? This cell uses the live SPARQL endpoint and counts shared chapters per author pair.

Show code

query = f'''
PREFIX wd: <{ENTITY_NS}>
PREFIX wdt: <{PROPERTY_NS}>
PREFIX rdfs: <http://www.w3.org/2000/01/rdf-schema#>
SELECT ?author1Id ?author1Label ?author2Id ?author2Label (COUNT(DISTINCT ?chapter) AS ?sharedChapters)
WHERE {{
  {{
    SELECT DISTINCT ?author1 ?author1Id ?author1Label ?author2 ?author2Id ?author2Label ?chapter
    WHERE {{
      ?author1 wdt:P1 wd:Q3998 ; wdt:P20 ?author1Id ; wdt:P27 ?chapter .
      ?author2 wdt:P1 wd:Q3998 ; wdt:P20 ?author2Id ; wdt:P27 ?chapter .
      FILTER(?author1Id < ?author2Id)
      OPTIONAL {{ ?author1 rdfs:label ?author1Label . FILTER(LANG(?author1Label) = "en") }}
      OPTIONAL {{ ?author2 rdfs:label ?author2Label . FILTER(LANG(?author2Label) = "en") }}
    }}
  }}
}}
GROUP BY ?author1Id ?author1Label ?author2Id ?author2Label
ORDER BY DESC(?sharedChapters) ?author1Label ?author2Label
LIMIT 20
'''

display(Markdown("**SPARQL query (copy/paste into ClimateKG Query UI: https://climatekg.tibwiki.io/query/)**"))
display(Markdown("```sparql\n" + query + "\n```"))
pairs_df = run_table(query)
if not pairs_df.empty:
    pairs_df = pairs_df.sort_values(["sharedChapters", "author1Label", "author2Label"], ascending=[False, True, True]).reset_index(drop=True)
    top_pairs = pairs_df[pairs_df["sharedChapters"] == pairs_df["sharedChapters"].max()]
    display(top_pairs[["author1Label", "author2Label", "sharedChapters"]])
else:
    display(pairs_df)

SPARQL query (copy/paste into ClimateKG Query UI: https://climatekg.tibwiki.io/query/)


PREFIX wd: <https://climatekg.tibwiki.io/entity/>
PREFIX wdt: <https://climatekg.tibwiki.io/prop/direct/>
PREFIX rdfs: <http://www.w3.org/2000/01/rdf-schema#>
SELECT ?author1Id ?author1Label ?author2Id ?author2Label (COUNT(DISTINCT ?chapter) AS ?sharedChapters)
WHERE {
  {
    SELECT DISTINCT ?author1 ?author1Id ?author1Label ?author2 ?author2Id ?author2Label ?chapter
    WHERE {
      ?author1 wdt:P1 wd:Q3998 ; wdt:P20 ?author1Id ; wdt:P27 ?chapter .
      ?author2 wdt:P1 wd:Q3998 ; wdt:P20 ?author2Id ; wdt:P27 ?chapter .
      FILTER(?author1Id < ?author2Id)
      OPTIONAL { ?author1 rdfs:label ?author1Label . FILTER(LANG(?author1Label) = "en") }
      OPTIONAL { ?author2 rdfs:label ?author2Label . FILTER(LANG(?author2Label) = "en") }
    }
  }
}
GROUP BY ?author1Id ?author1Label ?author2Id ?author2Label
ORDER BY DESC(?sharedChapters) ?author1Label ?author2Label
LIMIT 20

	author1Label	author2Label	sharedChapters
0	Aïda Diongue-Niang	Malte Meinshausen	3
1	Bronwyn Hayward	Joyashree Roy	3
2	Christopher Jones	June-yi Lee	3
3	David Dodman	Bronwyn Hayward	3
4	Gerhard Krinner	Aimée Slangen	3
5	Katherine Calvin	Detlef Van Vuuren	3

Question 6

Which institutions have the most authors across AR6? This cell uses the live SPARQL endpoint and counts distinct author IDs (P20) per affiliation (P26).

Show code

query = f'''
PREFIX wd: <{ENTITY_NS}>
PREFIX wdt: <{PROPERTY_NS}>
SELECT ?institution (COUNT(DISTINCT ?authorId) AS ?authors)
WHERE {{
  ?author wdt:P1 wd:Q3998 ;
          wdt:P20 ?authorId ;
          wdt:P26 ?institution .
}}
GROUP BY ?institution
ORDER BY DESC(?authors) ?institution
LIMIT 20
'''

display(Markdown("**SPARQL query (copy/paste into ClimateKG Query UI: https://climatekg.tibwiki.io/query/)**"))
display(Markdown("```sparql\n" + query + "\n```"))
institution_df = run_table(query).rename(columns={"institution": "Institution", "authors": "Authors"})
display(institution_df)

SPARQL query (copy/paste into ClimateKG Query UI: https://climatekg.tibwiki.io/query/)


PREFIX wd: <https://climatekg.tibwiki.io/entity/>
PREFIX wdt: <https://climatekg.tibwiki.io/prop/direct/>
SELECT ?institution (COUNT(DISTINCT ?authorId) AS ?authors)
WHERE {
  ?author wdt:P1 wd:Q3998 ;
          wdt:P20 ?authorId ;
          wdt:P26 ?institution .
}
GROUP BY ?institution
ORDER BY DESC(?authors) ?institution
LIMIT 20

	Institution	Authors
0	University of Cape Town	6
1	University of Leeds	6
2	Institute of Atmospheric Physics, Chinese Acad...	5
3	International Institute for Applied Systems An...	5
4	Met Office Hadley Centre	5
5	Tsinghua University	5
6	University of Bristol	5
7	University of Exeter	5
8	Australian National University	4
9	ETH Zurich	4
10	Federal University of Rio de Janeiro	4
11	Potsdam Institute for Climate Impact Research	4
12	University of Reading	4
13	Beijing Normal University	3
14	Environment and Climate Change Canada	3
15	Imperial College London	3
16	Institute of Marine Research	3
17	Lund University	3
18	Max Planck Institute for Meteorology	3
19	National Institute for Environmental Studies	3