Triple

T16909592
Position Surface form Disambiguated ID Type / Status
Subject Journeyman E410159 entity
Predicate mainCastMember P5563 FINISHED
Object Brian Howe 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: Brian Howe | Statement: [Journeyman, mainCastMember, Brian Howe]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Brian Howe
Context triple: [Journeyman, mainCastMember, Brian Howe]
  • A. Brian Howe chosen
    Brian Howe is an American character actor known for his work in film and television, including roles in projects like "Catch Me If You Can," "The Pursuit of Happyness," and various TV series.
  • B. Ian Howe
    Ian Howe is the primary antagonist in the film "National Treasure," a wealthy and ruthless treasure hunter who betrays the protagonist in his quest for historical riches.
  • C. John Howell
    John Howell is a British Conservative politician who has served as the Member of Parliament for the Henley constituency since winning the 2008 by-election.
  • D. Alan Howarth
    Alan Howarth is an American composer and sound designer best known for co-creating and expanding the iconic synthesizer-driven scores of many John Carpenter horror and science fiction films.
  • E. Karl Howman
    Karl Howman is a British actor best known for his television work in series such as "Brush Strokes" and "Mulberry."
  • 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_69d886c7b1e481908c3766dfa8c13458 completed April 10, 2026, 5:12 a.m.
NER Named-entity recognition batch_69e3ca3bdc3081908a9b4f6e63405348 completed April 18, 2026, 6:15 p.m.
Created at: April 10, 2026, 5:30 a.m.