Triple

T6519594
Position Surface form Disambiguated ID Type / Status
Subject SRW E148347 entity
Predicate fullName P16 FINISHED
Object Search/Retrieve Web Service
Search/Retrieve Web Service (SRW) is a standard web service protocol for querying and retrieving search results from remote databases and information retrieval systems over the web.
E605018 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: Search/Retrieve Web Service | Statement: [SRW, fullName, Search/Retrieve Web Service]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Search/Retrieve Web Service
Context triple: [SRW, fullName, Search/Retrieve Web Service]
  • A. 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.
  • B. ESearch
    ESearch is an NCBI E-utilities service that performs text-based searches of NCBI databases and returns lists of matching record identifiers.
  • C. Qwant
    Qwant is a French privacy-focused search engine that emphasizes user anonymity and does not track or profile its users.
  • D. Zeen web curation service
    Zeen web curation service was an online platform that allowed users to collect, organize, and present web content in magazine-style formats.
  • E. Yandex Search
    Yandex Search is a Russian-developed web search engine that powers Yandex’s ecosystem of online services and tools.
  • 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: Search/Retrieve Web Service
Triple: [SRW, fullName, Search/Retrieve Web Service]
Generated description
Search/Retrieve Web Service (SRW) is a standard web service protocol for querying and retrieving search results from remote databases and information retrieval systems over the web.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Search/Retrieve Web Service
Target entity description: Search/Retrieve Web Service (SRW) is a standard web service protocol for querying and retrieving search results from remote databases and information retrieval systems over the web.
  • A. 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.
  • B. ESearch
    ESearch is an NCBI E-utilities service that performs text-based searches of NCBI databases and returns lists of matching record identifiers.
  • C. Qwant
    Qwant is a French privacy-focused search engine that emphasizes user anonymity and does not track or profile its users.
  • D. Zeen web curation service
    Zeen web curation service was an online platform that allowed users to collect, organize, and present web content in magazine-style formats.
  • E. Yandex Search
    Yandex Search is a Russian-developed web search engine that powers Yandex’s ecosystem of online services and tools.
  • 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_69c687e68e748190baceb9298f32d3ed completed March 27, 2026, 1:36 p.m.
NER Named-entity recognition batch_69c6ac11d0e481908103c4b51de9521e completed March 27, 2026, 4:10 p.m.
NED1 Entity disambiguation (via context triple) batch_69c6d51af5308190928c97ceb5d5fa2d completed March 27, 2026, 7:06 p.m.
NEDg Description generation batch_69c6d6d9af148190ad9cd2cc31a70bb7 completed March 27, 2026, 7:13 p.m.
NED2 Entity disambiguation (via description) batch_69c6d98506b88190aae3b4d887744648 completed March 27, 2026, 7:24 p.m.
Created at: March 27, 2026, 1:45 p.m.