Triple

T13854541
Position Surface form Disambiguated ID Type / Status
Subject Hell or High Water (2016 film) E333028 entity
Predicate mainCharacter P1183 FINISHED
Object Toby Howard E1067284 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: Toby Howard | Statement: [Hell or High Water (2016 film), mainCharacter, Toby Howard]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Toby Howard
Context triple: [Hell or High Water (2016 film), mainCharacter, Toby Howard]
  • A. Toby Howard chosen
    Toby Howard is the desperate yet principled West Texas father and bank robber at the center of the neo-Western crime film "Hell or High Water."
  • B. Toby Gard
    Toby Gard is a British video game designer best known for creating the iconic Tomb Raider heroine Lara Croft.
  • C. Jon Shafer
    Jon Shafer is a video game designer best known as the lead designer of Sid Meier’s Civilization V.
  • D. Martin Hector
    Martin Hector was a prominent local businessman and civic leader from Fargo, North Dakota, best known for his contributions to the city that led to its main airport being named in his honor.
  • E. Richard Devine
    Richard Devine is an American electronic musician and sound designer known for his complex, experimental compositions and work in film, games, and technology.
  • 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_69d81c5ba13c8190839315f54768acfd completed April 9, 2026, 9:38 p.m.
NER Named-entity recognition batch_69de02db9c9c81909bb2d2fbfb7394b1 completed April 14, 2026, 9:03 a.m.
NED1 Entity disambiguation (via context triple) batch_69f7ce6c0c3c8190911b56b20c9eb955 completed May 3, 2026, 10:38 p.m.
Created at: April 9, 2026, 10:14 p.m.