Triple

T21752278
Position Surface form Disambiguated ID Type / Status
Subject SPI E536943 entity
Predicate hasConstituent P35 FINISHED
Object Novartis AG 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: Novartis AG | Statement: [SPI, hasConstituent, Novartis AG]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Novartis AG
Context triple: [SPI, hasConstituent, Novartis AG]
  • A. Novartis chosen
    Novartis is a global Swiss-based pharmaceutical company known for developing innovative medicines across a wide range of therapeutic areas.
  • B. Roche
    Roche is a common surname of French origin borne by various notable individuals across fields such as architecture, politics, and the arts.
  • C. Roche
    Roche is a major Swiss multinational healthcare company and one of the world’s leading pharmaceutical and diagnostics firms.
  • D. Roche
    Roche is a village and civil parish in Cornwall, England, known for its distinctive granite outcrop and historic chapel perched on Roche Rock.
  • E. Merck KGaA
    Merck KGaA is a German multinational science and technology company specializing in healthcare, life science, and electronics.
  • 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_69e0c46eab808190b848242d63a17c47 completed April 16, 2026, 11:13 a.m.
NER Named-entity recognition batch_69f01d8b8b9c8190b1f6a8bc25d69dbb completed April 28, 2026, 2:38 a.m.
Created at: April 16, 2026, 6:50 p.m.