Triple

T4021228
Position Surface form Disambiguated ID Type / Status
Subject SNIP E91282 entity
Predicate revisedBy P1121 FINISHED
Object CWTS Leiden
CWTS Leiden is a research center at Leiden University specializing in quantitative studies of science, technology, and innovation, best known for producing the global Leiden Ranking of universities.
 E407017 NE FINISHED

How this triple was built (4 steps)

Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.

NER Named-entity recognition gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: CWTS Leiden | Statement: [SNIP, revisedBy, CWTS Leiden]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: CWTS Leiden
Context triple: [SNIP, revisedBy, CWTS Leiden]
  • A. InCites
    InCites is a research analytics platform that provides citation-based metrics and benchmarking tools to evaluate institutional and researcher performance.
  • B. Web of Science
    Web of Science is a major multidisciplinary citation indexing and abstracting database widely used for academic research and bibliometric analysis.
  • C. Science Citation Index
    The Science Citation Index is a multidisciplinary citation database that tracks and indexes scientific journal articles to measure research impact and facilitate literature discovery.
  • D. Clarivate Analytics
    Clarivate Analytics is a global analytics company specializing in providing research, citation, patent, and intellectual property data and tools for academia, corporations, and governments.
  • E. Eigenfactor Score
    Eigenfactor Score is a journal influence metric that estimates the importance of scholarly journals by considering the origin and frequency of citations in a network-based model.
  • F. None of above. chosen
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg Description generation gpt-5.1
Instruction
Generate a one-sentence description of the target entity. 
You are given a context triple in the form (subject, predicate, object), where the object is the target entity. 
# Instructions
Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. 
Avoid repeating the information from the triple, unless really essential.
# Response Format
Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: CWTS Leiden
Triple: [SNIP, revisedBy, CWTS Leiden]
Generated description
CWTS Leiden is a research center at Leiden University specializing in quantitative studies of science, technology, and innovation, best known for producing the global Leiden Ranking of universities.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: CWTS Leiden
Target entity description: CWTS Leiden is a research center at Leiden University specializing in quantitative studies of science, technology, and innovation, best known for producing the global Leiden Ranking of universities.
  • A. InCites
    InCites is a research analytics platform that provides citation-based metrics and benchmarking tools to evaluate institutional and researcher performance.
  • B. Web of Science
    Web of Science is a major multidisciplinary citation indexing and abstracting database widely used for academic research and bibliometric analysis.
  • C. Science Citation Index
    The Science Citation Index is a multidisciplinary citation database that tracks and indexes scientific journal articles to measure research impact and facilitate literature discovery.
  • D. Clarivate Analytics
    Clarivate Analytics is a global analytics company specializing in providing research, citation, patent, and intellectual property data and tools for academia, corporations, and governments.
  • E. Eigenfactor Score
    Eigenfactor Score is a journal influence metric that estimates the importance of scholarly journals by considering the origin and frequency of citations in a network-based model.
  • F. None of above. chosen

Provenance (5 batches)

The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.

Step Stage Batch ID Status When
creating Elicitation batch_69aed9618b04819081750d979d2af098 completed March 9, 2026, 2:29 p.m.
NER Named-entity recognition batch_69aefacb4c208190b8dd595a534850b2 completed March 9, 2026, 4:52 p.m.
NED1 Entity disambiguation (via context triple) batch_69b54c7fd474819097766194ca8d165d completed March 14, 2026, 11:54 a.m.
NEDg Description generation batch_69b54dd51ef48190974bb190d32016bc completed March 14, 2026, noon
NED2 Entity disambiguation (via description) batch_69b54e498320819088fea96b83564c69 completed March 14, 2026, 12:02 p.m.
Created at: March 9, 2026, 3:35 p.m.