Triple

T22891709
Position Surface form Disambiguated ID Type / Status
Subject Split Second E568057 entity
Predicate director P255 FINISHED
Object Tony Maylam 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: Tony Maylam | Statement: [Split Second, director, Tony Maylam]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Tony Maylam
Context triple: [Split Second, director, Tony Maylam]
  • A. Tony Maylam chosen
    Tony Maylam is a British film director best known for his work in horror and documentary filmmaking, including the cult slasher film "The Burning."
  • B. Charlie Hugall
    Charlie Hugall is a British record producer and mixer known for his work with prominent indie and pop artists.
  • C. Ian Mackley
    Ian Mackley is the husband of British comedian and television personality Julian Clary.
  • D. Ian Maxtone-Graham
    Ian Maxtone-Graham is an American television writer and producer best known for his long-running work on "The Simpsons" and other animated comedy projects.
  • E. Colin Tilley
    Colin Tilley is an American music video director known for his visually dynamic, narrative-driven work with major artists across pop, hip-hop, and Latin music.
  • 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_69e2458c23ec81908fa2570692c6614f completed April 17, 2026, 2:37 p.m.
NER Named-entity recognition batch_69f17fc59e108190a22f90c2439830fb completed April 29, 2026, 3:49 a.m.
Created at: April 17, 2026, 3:40 p.m.