Triple

T15211050
Position Surface form Disambiguated ID Type / Status
Subject Brian Banks E363514 entity
Predicate producer P490 FINISHED
Object Brian Banks E363514 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: Brian Banks | Statement: [Brian Banks, producer, Brian Banks]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Brian Banks
Context triple: [Brian Banks, producer, Brian Banks]
  • A. Brian Banks chosen
    Brian Banks is a 2018 biographical drama film about a promising high school football player whose NFL dreams are derailed by a wrongful conviction and his subsequent fight to clear his name.
  • B. Brian Banks
    Brian Banks is a composer best known for his work on the film score for "Young Guns."
  • C. Yusef Salaam
    Yusef Salaam is a criminal justice reform advocate, author, and member of the Exonerated Five who was wrongfully convicted in the Central Park jogger case and later exonerated.
  • D. Michael Vick
    Michael Vick is a former NFL quarterback best known for his electrifying dual-threat playmaking ability, particularly during his early career with the Atlanta Falcons.
  • E. Andre Lamont Johnson
    Andre Lamont Johnson is a former American football wide receiver best known for his prolific NFL career, primarily with the Houston Texans.
  • 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_69d85a0b78bc8190b6e5ad51a2c4cfc5 completed April 10, 2026, 2:01 a.m.
NER Named-entity recognition batch_69e0076ad4ec81908d36f541fca08d72 completed April 15, 2026, 9:47 p.m.
NED1 Entity disambiguation (via context triple) batch_69fed33f9abc8190bf8166c1fd9fcac6 completed May 9, 2026, 6:25 a.m.
Created at: April 10, 2026, 3:11 a.m.