Triple

T11171751
Position Surface form Disambiguated ID Type / Status
Subject Legend (2015 film) E264288 entity
Predicate editedBy P1954 FINISHED
Object Peter McNulty E356549 NE FINISHED

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 McNulty | Statement: [Legend (2015 film), editedBy, Peter McNulty]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Peter McNulty
Context triple: [Legend (2015 film), editedBy, Peter McNulty]
  • A. Peter McNulty chosen
    Peter McNulty is a film editor known for his work on feature films including the military drama "Megan Leavey."
  • B. Patrick McNulty
    Patrick McNulty is the central character in the Twilight Zone episode "A Kind of Stopwatch," a talkative and meddlesome man who acquires a magical stopwatch that can freeze time.
  • C. Sean McNulty
    Sean McNulty is a minor character in the television series "The Wire," known primarily as one of detective Jimmy McNulty's sons.
  • D. Tony McNulty
    Tony McNulty is a British Labour politician who served as Member of Parliament and held ministerial roles including Minister of State for Security, Counter-Terrorism, Crime and Policing.
  • E. Matthew McNulty
    Matthew McNulty is a British actor known for his work in film and television, including roles in series like "Misfits," "The Mill," and "Versailles."
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (3 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_69d6aa9dafac8190bd90d2c74f661aa7 completed April 8, 2026, 7:21 p.m.
NER Named-entity recognition batch_69d7e89660208190b1d9e91529f5d246 completed April 9, 2026, 5:57 p.m.
NED1 Entity disambiguation (via context triple) batch_69f63ed654848190b53e8b64d81eb143 completed May 2, 2026, 6:13 p.m.
Created at: April 8, 2026, 9:29 p.m.