Triple

T6447998
Position Surface form Disambiguated ID Type / Status
Subject Western University E139790 entity
Predicate shortName P43 FINISHED
Object Western E139790 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: Western | Statement: [Western University, shortName, Western]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Western
Context triple: [Western University, shortName, Western]
  • A. Western chosen
    Western is a Canadian public research university located in London, Ontario, known for its strong programs in business, health sciences, and social sciences.
  • B. Western
    Western is a film genre typically set in the American frontier, featuring cowboys, outlaws, lawmen, and themes of rugged individualism, justice, and survival in a harsh, lawless landscape.
  • C. Western
    Western is a Chicago 'L' rapid transit station on the CTA Pink Line serving the city's West Side.
  • D. West
    West is a prominent American legal publishing company best known for producing case law reporters, legal research tools, and the Westlaw online database.
  • E. West
    West is the surname of Kanye West, the influential American rapper, producer, and fashion designer.
  • 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_69c008b301948190a35854e5284dc822 completed March 22, 2026, 3:20 p.m.
NER Named-entity recognition batch_69c069afd8c48190b3cab580c813ecab completed March 22, 2026, 10:14 p.m.
NED1 Entity disambiguation (via context triple) batch_69c64bcfc7388190877ad702ea44802d completed March 27, 2026, 9:20 a.m.
Created at: March 22, 2026, 4:47 p.m.