Triple

T14254477
Position Surface form Disambiguated ID Type / Status
Subject MeSH E353350 entity
Predicate fullName P16 FINISHED
Object Medical Subject Headings E353351 NE FINISHED

How this triple was built (2 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: Medical Subject Headings | Statement: [MeSH, fullName, Medical Subject Headings]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Medical Subject Headings
Context triple: [MeSH, fullName, Medical Subject Headings]
  • A. Medical Subject Headings chosen
    Medical Subject Headings (MeSH) is a comprehensive controlled vocabulary thesaurus used for indexing, cataloging, and searching biomedical and health-related information.
  • B. MeSH
    MeSH (Medical Subject Headings) is a comprehensive controlled vocabulary thesaurus used for indexing, cataloging, and searching biomedical and health-related information.
  • C. MeSH Supplementary Concept Records
    MeSH Supplementary Concept Records are additional, more granular entries in the Medical Subject Headings system used to index and retrieve information on specific chemicals, drugs, and other specialized biomedical concepts not covered by main MeSH headings.
  • D. SNOMED CT
    SNOMED CT is a comprehensive, multilingual clinical healthcare terminology used worldwide to standardize the recording and sharing of medical information in electronic health records.
  • E. Unified Medical Language System
    The Unified Medical Language System is a comprehensive set of files and software from the U.S. National Library of Medicine that integrates and standardizes numerous biomedical vocabularies and coding systems to support interoperability and advanced information retrieval in healthcare and research.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (3 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_69d8278c43e08190824146f4632b89a5 completed April 9, 2026, 10:26 p.m.
NER Named-entity recognition batch_69de6297f38c819090d7c7fd8bfa2e9e completed April 14, 2026, 3:51 p.m.
NED1 Entity disambiguation (via context triple) batch_69fd3d127f0c81908dea42ca09c1abda completed May 8, 2026, 1:32 a.m.
Created at: April 10, 2026, 1:09 a.m.