Triple

T17316396
Position Surface form Disambiguated ID Type / Status
Subject Henry Bromell E420435 entity
Predicate name P16 FINISHED
Object Henry Bromell 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: Henry Bromell | Statement: [Henry Bromell, name, Henry Bromell]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Henry Bromell
Context triple: [Henry Bromell, name, Henry Bromell]
  • A. Henry Bromell chosen
    Henry Bromell was an American writer, producer, and director best known for his work on acclaimed television dramas such as "Homeland" and "Homicide: Life on the Street."
  • B. Hugh Millard
    Hugh Millard is a British diplomat who has served as Commissioner of the British Antarctic Territory.
  • C. Henry Heath
    Henry Heath is a relatively obscure individual whose name is notably associated with the surname Heath.
  • D. Alan Hume
    Alan Hume was a British cinematographer known for his work on several James Bond films and other major features such as "Return of the Jedi."
  • E. Andrew Holbrook
    Andrew Holbrook is a professional mixed martial artist known for competing in major promotions such as the UFC in the lightweight division.
  • 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_69d889d22b848190a4663d0b8f8f76e7 completed April 10, 2026, 5:25 a.m.
NER Named-entity recognition batch_69e4399d2fcc81909916302f141e236b completed April 19, 2026, 2:10 a.m.
Created at: April 10, 2026, 5:43 a.m.