Triple

T22932109
Position Surface form Disambiguated ID Type / Status
Subject ESummary E569468 entity
Predicate operatesOn P23 FINISHED
Object PubChem
PubChem is a free, publicly accessible database maintained by the National Institutes of Health that provides comprehensive information on the biological activities and chemical properties of small molecules and compounds.
 E1562328 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: PubChem | Statement: [ESummary, operatesOn, PubChem]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: PubChem
Context triple: [ESummary, operatesOn, PubChem]
  • A. PubChem Compound
    PubChem Compound is a public database record type in the PubChem system that provides detailed chemical information about individual small molecules, including their structures, properties, and biological activities.
  • B. PubChem Substance
    PubChem Substance is a component of the PubChem database that stores detailed records of chemical substances as submitted by various data contributors, including their structures, identifiers, and related information.
  • C. PaperChem
    PaperChem is a specialized database focused on chemical and materials science information related to paper and pulp research, accessible through the Engineering Village platform.
  • D. SciFinder-n
    SciFinder-n is a comprehensive research discovery platform from Chemical Abstracts Service that enables scientists to search and analyze chemical substances, reactions, literature, and related scientific data.
  • E. PubChem BioAssay
    PubChem BioAssay is a public database of biological activity results from high-throughput screening and other assays, used to link chemical substances with their biological effects.
  • 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: PubChem
Triple: [ESummary, operatesOn, PubChem]
Generated description
PubChem is a free, publicly accessible database maintained by the National Institutes of Health that provides comprehensive information on the biological activities and chemical properties of small molecules and compounds.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: PubChem
Target entity description: PubChem is a free, publicly accessible database maintained by the National Institutes of Health that provides comprehensive information on the biological activities and chemical properties of small molecules and compounds.
  • A. PubChem Compound
    PubChem Compound is a public database record type in the PubChem system that provides detailed chemical information about individual small molecules, including their structures, properties, and biological activities.
  • B. PubChem Substance
    PubChem Substance is a component of the PubChem database that stores detailed records of chemical substances as submitted by various data contributors, including their structures, identifiers, and related information.
  • C. PaperChem
    PaperChem is a specialized database focused on chemical and materials science information related to paper and pulp research, accessible through the Engineering Village platform.
  • D. SciFinder-n
    SciFinder-n is a comprehensive research discovery platform from Chemical Abstracts Service that enables scientists to search and analyze chemical substances, reactions, literature, and related scientific data.
  • E. PubChem BioAssay
    PubChem BioAssay is a public database of biological activity results from high-throughput screening and other assays, used to link chemical substances with their biological effects.
  • 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_69e2458f7d008190901dccbaebeaba24 completed April 17, 2026, 2:37 p.m.
NER Named-entity recognition batch_69f1813260608190bb9e1ca704c7e12f completed April 29, 2026, 3:55 a.m.
NED1 Entity disambiguation (via context triple) batch_6a0bc24cd43c81908111b62945f91dda completed May 19, 2026, 1:52 a.m.
NEDg Description generation batch_6a0bc407cd448190bd843360d65fdf22 completed May 19, 2026, 1:59 a.m.
NED2 Entity disambiguation (via description) batch_6a0bc46fd3d0819094a532a8d6a0b9b2 completed May 19, 2026, 2:01 a.m.
Created at: April 17, 2026, 3:44 p.m.