Triple

T22023314
Position Surface form Disambiguated ID Type / Status
Subject Taken (TV series) E543894 entity
Predicate portraysFictionalCharacter P1668 FINISHED
Object Bryan Mills 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: Bryan Mills | Statement: [Taken (TV series), portraysFictionalCharacter, Bryan Mills]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Bryan Mills
Context triple: [Taken (TV series), portraysFictionalCharacter, Bryan Mills]
  • A. Bryan Mills chosen
    Bryan Mills is the highly skilled former CIA operative and fiercely protective father portrayed by Liam Neeson in the Taken film series.
  • B. Bryan Michael Mills
    Bryan Michael Mills is a composer and musician known for creating the musical score for the film "Sweet Country."
  • C. Chris Ridenhour
    Chris Ridenhour is a film composer known for scoring numerous low-budget genre movies, including works produced by The Asylum.
  • D. Sean Biggerstaff
    Sean Biggerstaff is a Scottish actor best known for playing Oliver Wood in the Harry Potter film series.
  • E. Brian Sipe
    Brian Sipe is a former NFL quarterback best known for his MVP-winning 1980 season with the Cleveland Browns as leader of the "Kardiac Kids."
  • 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_69e11e2e8ea4819084210fe06d3a1b8d completed April 16, 2026, 5:36 p.m.
NER Named-entity recognition batch_69f127c9959481908da6bed356199f75 completed April 28, 2026, 9:34 p.m.
Created at: April 16, 2026, 8:23 p.m.