Triple

T10131423
Position Surface form Disambiguated ID Type / Status
Subject Michael Small E226346 entity
Predicate notableWork P4 FINISHED
Object The Driver E734407 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: The Driver | Statement: [Michael Small, notableWork, The Driver]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: The Driver
Context triple: [Michael Small, notableWork, The Driver]
  • A. The Driver
    The Driver is the laconic, unnamed street racer portrayed by James Taylor in the 1971 cult road movie "Two-Lane Blacktop."
  • B. The Driver chosen
    The Driver is a 1978 neo-noir crime thriller film written and directed by Walter Hill, centered on a taciturn, highly skilled getaway driver involved in a tense cat-and-mouse game with a relentless detective.
  • C. The Drive
    The Drive is a vibrant, culturally diverse neighborhood and commercial district in East Vancouver known for its eclectic shops, restaurants, and arts scene.
  • D. Stuber
    Stuber is a 2019 action-comedy film about a mild-mannered rideshare driver who gets roped into helping a tough cop track down a criminal, starring Kumail Nanjiani and Dave Bautista.
  • E. Crank
    Crank is a 2006 high-octane action thriller film starring Jason Statham as a poisoned hitman racing against time to stay alive.
  • 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_69ca843057b48190a86730167f5d6b98 completed March 30, 2026, 2:09 p.m.
NER Named-entity recognition batch_69cdd33557a88190b5fb1938646d8532 completed April 2, 2026, 2:23 a.m.
NED1 Entity disambiguation (via context triple) batch_69d2cc8462ac81908485115bcf2a2d19 completed April 5, 2026, 8:56 p.m.
Created at: March 30, 2026, 9:06 p.m.