Triple

T9720449
Position Surface form Disambiguated ID Type / Status
Subject Steve McQueen E235450 entity
Predicate familyName P18 FINISHED
Object McQueen E275923 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: McQueen | Statement: [Steve McQueen, familyName, McQueen]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: McQueen
Context triple: [Steve McQueen, familyName, McQueen]
  • A. McQueen chosen
    McQueen is the surname of the influential British fashion designer Alexander McQueen, renowned for his innovative, theatrical, and often provocative haute couture.
  • B. Ford v Ferrari
    Ford v Ferrari is a 2019 biographical sports drama film that chronicles Ford Motor Company's quest to defeat Ferrari at the 1966 24 Hours of Le Mans, starring Matt Damon and Christian Bale.
  • C. L’Auto
    L’Auto was a French sports newspaper best known for creating and organizing the Tour de France.
  • D. Mario Maserati
    Mario Maserati was an Italian automotive engineer and entrepreneur best known as one of the founding brothers behind the Maserati luxury sports car brand.
  • E. The Stig
    The Stig is the mysterious, helmeted racing driver on the British TV show Top Gear, known for anonymously setting lap times and testing cars.
  • 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_69ca84d0123c819096f9dc3b6abb0881 completed March 30, 2026, 2:12 p.m.
NER Named-entity recognition batch_69cd9e419c2c8190b325d5fd692c6000 completed April 1, 2026, 10:37 p.m.
NED1 Entity disambiguation (via context triple) batch_69d19f9c4ff4819098ad941438abbe3c completed April 4, 2026, 11:32 p.m.
Created at: March 30, 2026, 8:20 p.m.