Triple

T15294522
Position Surface form Disambiguated ID Type / Status
Subject Twin Peaks: Fire Walk with Me E365617 entity
Predicate stars P1956 FINISHED
Object Moira Kelly E189346 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: Moira Kelly | Statement: [Twin Peaks: Fire Walk with Me, stars, Moira Kelly]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Moira Kelly
Context triple: [Twin Peaks: Fire Walk with Me, stars, Moira Kelly]
  • A. Moira Kelly chosen
    Moira Kelly is an American actress best known for her film and television roles, including voicing the adult Nala in Disney’s "The Lion King" and starring in series like "The West Wing" and "One Tree Hill."
  • B. Finola Jones
    Finola Jones is a British MI6 agent and one of the two central protagonists investigating mysterious alien wreckage in the science fiction television series "Debris."
  • C. Finola Hughes
    Finola Hughes is a British actress, television host, and dancer best known for her long-running role as Anna Devane on the soap opera "General Hospital."
  • D. Finola Dwyer
    Finola Dwyer is a New Zealand-born, London-based film producer known for acclaimed films such as "An Education" and "Brooklyn."
  • E. Oona Flaherty
    Oona Flaherty is a film editor known for her work on the 2023 adaptation of "Are You There God? It’s Me, Margaret."
  • 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_69d85a103d9081908c1ea6c4c73ac8e3 completed April 10, 2026, 2:01 a.m.
NER Named-entity recognition batch_69e03682ea488190ac82fdbd0e855d34 completed April 16, 2026, 1:08 a.m.
NED1 Entity disambiguation (via context triple) batch_69ff2cea6bb88190a6d6f7c55daa4677 completed May 9, 2026, 12:47 p.m.
Created at: April 10, 2026, 3:15 a.m.