Triple

T1793148
Position Surface form Disambiguated ID Type / Status
Subject AlphaFold E39542 entity
Predicate dataSource P409 FINISHED
Object UniProt protein sequences
UniProt protein sequences are a comprehensive, curated collection of protein sequence data that serves as a primary reference resource for protein information in biological and biomedical research.
 E200557 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: UniProt protein sequences | Statement: [AlphaFold, dataSource, UniProt protein sequences]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: UniProt protein sequences
Context triple: [AlphaFold, dataSource, UniProt protein sequences]
  • A. NCBI E-utilities API
    The NCBI E-utilities API is a set of programmatic web services that allow automated querying, retrieval, and integration of data from NCBI databases such as PubMed.
  • B. National Center for Biotechnology Information
    The National Center for Biotechnology Information (NCBI) is a U.S. government bioinformatics institution that develops and hosts major biological databases and tools for biomedical research.
  • C. Entrez system
    The Entrez system is an integrated search and retrieval platform from the National Center for Biotechnology Information (NCBI) that provides unified access to a wide range of biomedical databases, including literature, sequences, genomes, and more.
  • D. AlphaFold
    AlphaFold is an artificial intelligence system developed by DeepMind that predicts protein 3D structures from amino acid sequences with unprecedented accuracy, revolutionizing structural biology.
  • E. NCBI Bookshelf
    NCBI Bookshelf is a free online resource from the National Center for Biotechnology Information that provides access to a wide range of biomedical books, reports, and other full-text scholarly literature.
  • 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: UniProt protein sequences
Triple: [AlphaFold, dataSource, UniProt protein sequences]
Generated description
UniProt protein sequences are a comprehensive, curated collection of protein sequence data that serves as a primary reference resource for protein information in biological and biomedical research.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: UniProt protein sequences
Target entity description: UniProt protein sequences are a comprehensive, curated collection of protein sequence data that serves as a primary reference resource for protein information in biological and biomedical research.
  • A. NCBI E-utilities API
    The NCBI E-utilities API is a set of programmatic web services that allow automated querying, retrieval, and integration of data from NCBI databases such as PubMed.
  • B. National Center for Biotechnology Information
    The National Center for Biotechnology Information (NCBI) is a U.S. government bioinformatics institution that develops and hosts major biological databases and tools for biomedical research.
  • C. Entrez system
    The Entrez system is an integrated search and retrieval platform from the National Center for Biotechnology Information (NCBI) that provides unified access to a wide range of biomedical databases, including literature, sequences, genomes, and more.
  • D. AlphaFold
    AlphaFold is an artificial intelligence system developed by DeepMind that predicts protein 3D structures from amino acid sequences with unprecedented accuracy, revolutionizing structural biology.
  • E. NCBI Bookshelf
    NCBI Bookshelf is a free online resource from the National Center for Biotechnology Information that provides access to a wide range of biomedical books, reports, and other full-text scholarly literature.
  • 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_69a88631854081909723959921e45c2b completed March 4, 2026, 7:21 p.m.
NER Named-entity recognition batch_69aa653b02448190bc475bc22187f5b0 completed March 6, 2026, 5:25 a.m.
NED1 Entity disambiguation (via context triple) batch_69adb5d26afc81909675064289d3a5b8 completed March 8, 2026, 5:45 p.m.
NEDg Description generation batch_69adb69b142c81909dd8bd40e8e440ad completed March 8, 2026, 5:49 p.m.
NED2 Entity disambiguation (via description) batch_69adb8bac99081908cf126d42c609559 completed March 8, 2026, 5:58 p.m.
Created at: March 4, 2026, 7:32 p.m.