Triple

T22855852
Position Surface form Disambiguated ID Type / Status
Subject Zulu Dawn E566477 entity
Predicate director P255 FINISHED
Object Douglas Hickox 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: Douglas Hickox | Statement: [Zulu Dawn, director, Douglas Hickox]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Douglas Hickox
Context triple: [Zulu Dawn, director, Douglas Hickox]
  • A. Douglas Hickox chosen
    Douglas Hickox was a British film and television director known for works such as "Theatre of Blood" and "Zulu Dawn."
  • B. Frank Yallop
    Frank Yallop is a former Canadian international defender and successful soccer coach best known for leading the San Jose Earthquakes to multiple MLS Cup titles.
  • C. Sir Brian Hutton
    Sir Brian Hutton was a prominent British judge who served as Lord Chief Justice of Northern Ireland and later led the high-profile Hutton Inquiry into the death of weapons expert Dr. David Kelly.
  • D. Ian Rickson
    Ian Rickson is a British theatre director best known for his acclaimed work at London’s Royal Court Theatre and on numerous high-profile West End and Broadway productions.
  • E. Tommy Docherty
    Tommy Docherty was a Scottish football player and manager best known for managing Manchester United in the 1970s.
  • 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_69e2458750b481908a8e4cf4609cc6cf completed April 17, 2026, 2:36 p.m.
NER Named-entity recognition batch_69f17ebc6a088190890f2474f18a10eb completed April 29, 2026, 3:45 a.m.
Created at: April 17, 2026, 3:37 p.m.