Triple

T22448131
Position Surface form Disambiguated ID Type / Status
Subject Gunpowder E554916 entity
Predicate starring P1507 FINISHED
Object Peter Mullan 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: Peter Mullan | Statement: [Gunpowder, starring, Peter Mullan]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Peter Mullan
Context triple: [Gunpowder, starring, Peter Mullan]
  • A. Peter Mullan chosen
    Peter Mullan is a Scottish actor and filmmaker known for his intense character roles in films such as "My Name Is Joe," "Trainspotting," and "War Horse."
  • B. Kevin Macdonald
    Kevin Macdonald is a Scottish filmmaker best known for directing acclaimed documentaries and feature films such as "One Day in September" and "The Last King of Scotland."
  • C. George Swinton
    George Swinton was a notable member of the prominent Swinton family, recognized for his role in public service and contributions to British civic life.
  • D. Warren Moore
    Warren Moore was an American songwriter and member of the Miracles, best known for co-writing several Motown hits including "The Tracks of My Tears."
  • E. Michael Caton-Jones
    Michael Caton-Jones is a Scottish film director known for works such as "Scandal," "Rob Roy," and "The Jackal."
  • 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_69e11e5113208190ab58c6b595f9d1d0 completed April 16, 2026, 5:37 p.m.
NER Named-entity recognition batch_69f15b48be0481909f4601b732424e5b completed April 29, 2026, 1:13 a.m.
Created at: April 16, 2026, 8:48 p.m.