Triple

T2504158
Position Surface form Disambiguated ID Type / Status
Subject Mycobacterium tuberculosis E52537 entity
Predicate antibioticTreatment P4714 FINISHED
Object isoniazid LITERAL 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: isoniazid | Statement: [Mycobacterium tuberculosis, antibioticTreatment, isoniazid]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: antibioticTreatment
Context triple: [Mycobacterium tuberculosis, antibioticTreatment, isoniazid]
  • A. treats
    Indicates that one entity provides medical care or therapeutic intervention to another entity.
  • B. treatment chosen
    Indicates that one entity is used as a medical or therapeutic intervention to address, manage, or cure a condition affecting another entity.
  • C. exportTreatment
    Indicates the action or process of sending or transferring a treatment (such as a medical, data, or procedural treatment) from one system, location, or context to another for external use or application.
  • D. importTreatment
    Indicates that one entity brings or transfers a treatment or therapeutic intervention into another context, system, or location for use or application.
  • E. commonRouteOfAdministration
    Indicates that two or more substances share the same typical method or pathway by which they are administered to a subject.
  • F. None of above.

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_69ab4957b3a88190adf968ae0c1b931c completed March 6, 2026, 9:38 p.m.
NER Named-entity recognition batch_69abd1cd2db0819087d21ec49ffd9585 completed March 7, 2026, 7:20 a.m.
PD Predicate disambiguation batch_69abd0bba5348190bb4637d3165cb339 completed March 7, 2026, 7:16 a.m.
Created at: March 6, 2026, 9:46 p.m.