Triple

T19773794
Position Surface form Disambiguated ID Type / Status
Subject CCDC E474953 entity
Predicate curates P5107 FINISHED
Object Cambridge Structural Database — NE NERFINISHED

How this triple was built (3 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: Cambridge Structural Database | Statement: [CCDC, curates, Cambridge Structural Database]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Cambridge Structural Database
Context triple: [CCDC, curates, Cambridge Structural Database]
  • A. Cambridge Crystallographic Data Centre
    The Cambridge Crystallographic Data Centre is a leading research organization that curates and distributes the world’s primary database of small-molecule organic and metal-organic crystal structures for the scientific community.
  • B. Crystallographic Information Framework
    The Crystallographic Information Framework is a standardized data format and ontology used worldwide for representing, exchanging, and archiving crystallographic and related structural science data.
  • C. IUCrData
    IUCrData is an open-access crystallography data journal published by the International Union of Crystallography, focusing on brief reports of crystal structure determinations and related datasets.
  • D. Reaxys
    Reaxys is a comprehensive chemistry research database and workflow tool that provides curated information on chemical substances, reactions, and properties for scientists and researchers.
  • E. World Directory of Crystallographers
    The World Directory of Crystallographers is a comprehensive international reference listing professional crystallographers and related scientists, often used to facilitate collaboration and communication within the crystallography community.
  • F. None of above. chosen
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Cambridge Structural Database
Target entity description: The Cambridge Structural Database is a comprehensive repository of small-molecule organic and metal-organic crystal structures widely used for research in chemistry and materials science.
  • A. Cambridge Crystallographic Data Centre chosen
    The Cambridge Crystallographic Data Centre is a leading research organization that curates and distributes the world’s primary database of small-molecule organic and metal-organic crystal structures for the scientific community.
  • B. Crystallographic Information Framework
    The Crystallographic Information Framework is a standardized data format and ontology used worldwide for representing, exchanging, and archiving crystallographic and related structural science data.
  • C. IUCrData
    IUCrData is an open-access crystallography data journal published by the International Union of Crystallography, focusing on brief reports of crystal structure determinations and related datasets.
  • D. Reaxys
    Reaxys is a comprehensive chemistry research database and workflow tool that provides curated information on chemical substances, reactions, and properties for scientists and researchers.
  • E. World Directory of Crystallographers
    The World Directory of Crystallographers is a comprehensive international reference listing professional crystallographers and related scientists, often used to facilitate collaboration and communication within the crystallography community.
  • F. None of above.

Provenance (2 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_69d8e51a43a08190956bc6df13c91a77 completed April 10, 2026, 11:55 a.m.
NER Named-entity recognition batch_69e6535e450c8190a2628245ae0d0bd3 completed April 20, 2026, 4:25 p.m.
Created at: April 10, 2026, 1:48 p.m.