Triple

T7930818
Position Surface form Disambiguated ID Type / Status
Subject AbbVie E184183 entity
Predicate acquired P2511 FINISHED
Object Allergan E474948 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: Allergan | Statement: [AbbVie, acquired, Allergan]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Allergan
Context triple: [AbbVie, acquired, Allergan]
  • A. Allergan chosen
    Allergan is a global pharmaceutical company best known for developing branded drugs and medical aesthetics products, including Botox.
  • B. Alcon
    Alcon is a global eye care company specializing in ophthalmic pharmaceuticals, surgical equipment, and vision care products.
  • C. Bausch + Lomb
    Bausch + Lomb is a global eye health company best known for its contact lenses, lens care products, and ophthalmic pharmaceuticals.
  • D. Johnson & Johnson
    Johnson & Johnson is a multinational healthcare conglomerate best known for its pharmaceuticals, medical devices, and consumer health products.
  • E. Perrigo
    Perrigo is a global healthcare company best known for manufacturing and distributing over-the-counter and generic prescription pharmaceuticals, consumer healthcare products, and nutritional items.
  • 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_69ca8290c21c8190906a5ca6fe2b03c4 completed March 30, 2026, 2:02 p.m.
NER Named-entity recognition batch_69cb3accc388819087065ebe7d5d9591 completed March 31, 2026, 3:09 a.m.
NED1 Entity disambiguation (via context triple) batch_69cb5c01602081908ea1af24785260ff completed March 31, 2026, 5:30 a.m.
Created at: March 30, 2026, 5:07 p.m.