Triple

T6098397
Position Surface form Disambiguated ID Type / Status
Subject NCBI E-utilities API E135932 entity
Predicate hasComponent P35 FINISHED
Object ESearch
ESearch is an NCBI E-utilities service that performs text-based searches of NCBI databases and returns lists of matching record identifiers.
 E569467 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: ESearch | Statement: [NCBI E-utilities API, hasComponent, ESearch]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: ESearch
Context triple: [NCBI E-utilities API, hasComponent, ESearch]
  • A. Search and Discovery
    Search and Discovery is a regular Physics Today section that highlights notable recent advances and findings across the physical sciences.
  • B. Internet search
    Internet search is the process of using specialized software and algorithms to locate relevant information across the World Wide Web based on user queries.
  • C. Alexander Search
    Alexander Search is one of Fernando Pessoa’s English-writing heteronyms, used to compose poetry and prose distinct in style and persona from Pessoa himself.
  • D. Spotlight search
    Spotlight search is macOS’s built-in search and indexing feature that lets users quickly find files, apps, and information across their system and the web.
  • E. Qwant
    Qwant is a French privacy-focused search engine that emphasizes user anonymity and does not track or profile its users.
  • 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: ESearch
Triple: [NCBI E-utilities API, hasComponent, ESearch]
Generated description
ESearch is an NCBI E-utilities service that performs text-based searches of NCBI databases and returns lists of matching record identifiers.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: ESearch
Target entity description: ESearch is an NCBI E-utilities service that performs text-based searches of NCBI databases and returns lists of matching record identifiers.
  • A. Search and Discovery
    Search and Discovery is a regular Physics Today section that highlights notable recent advances and findings across the physical sciences.
  • B. Internet search
    Internet search is the process of using specialized software and algorithms to locate relevant information across the World Wide Web based on user queries.
  • C. Alexander Search
    Alexander Search is one of Fernando Pessoa’s English-writing heteronyms, used to compose poetry and prose distinct in style and persona from Pessoa himself.
  • D. Spotlight search
    Spotlight search is macOS’s built-in search and indexing feature that lets users quickly find files, apps, and information across their system and the web.
  • E. Qwant
    Qwant is a French privacy-focused search engine that emphasizes user anonymity and does not track or profile its users.
  • 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_69c0087cd3c48190b459848c72d84eb1 completed March 22, 2026, 3:19 p.m.
NER Named-entity recognition batch_69c05a9a02888190ac201acd14c3fc31 completed March 22, 2026, 9:09 p.m.
NED1 Entity disambiguation (via context triple) batch_69c125475548819086b733a80056eba5 completed March 23, 2026, 11:34 a.m.
NEDg Description generation batch_69c128753cd8819096edb3c817bfae10 completed March 23, 2026, 11:48 a.m.
NED2 Entity disambiguation (via description) batch_69c129134ce08190ada54a7b3eda27f4 completed March 23, 2026, 11:50 a.m.
Created at: March 22, 2026, 4:12 p.m.