Triple

T22690420
Position Surface form Disambiguated ID Type / Status
Subject larotrectinib E561035 entity
Predicate hasINN P23160 FINISHED
Object larotrectinib NE NERFINISHED

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: larotrectinib | Statement: [larotrectinib, hasINN, larotrectinib]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: larotrectinib
Context triple: [larotrectinib, hasINN, larotrectinib]
  • A. larotrectinib chosen
    Larotrectinib is a targeted cancer therapy that selectively inhibits TRK fusion proteins and is used to treat solid tumors harboring NTRK gene fusions regardless of tumor site.
  • B. selpercatinib
    Selpercatinib is a targeted cancer therapy drug that selectively inhibits RET kinase to treat certain RET-altered thyroid and non-small cell lung cancers.
  • C. tirabrutinib
    Tirabrutinib is a selective small-molecule Bruton’s tyrosine kinase (BTK) inhibitor developed as a targeted therapy for certain B-cell malignancies and autoimmune diseases.
  • D. neratinib
    Neratinib is an oral tyrosine kinase inhibitor used primarily in the treatment of HER2-positive breast cancer, often as extended adjuvant therapy after trastuzumab.
  • E. fam-trastuzumab deruxtecan
    Fam-trastuzumab deruxtecan is an antibody–drug conjugate used primarily to treat HER2-positive cancers by delivering a cytotoxic payload directly to HER2-expressing tumor cells.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 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_69e2454d71b48190a1f80af9f82b6fcf completed April 17, 2026, 2:35 p.m.
NER Named-entity recognition batch_69f1789a1fd08190bce5fa0babe695d3 completed April 29, 2026, 3:18 a.m.
Created at: April 17, 2026, 3:13 p.m.