Triple

T20525715
Position Surface form Disambiguated ID Type / Status
Subject Phantom Lady E503929 entity
Predicate stars P1956 FINISHED
Object Ella Raines 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: Ella Raines | Statement: [Phantom Lady, stars, Ella Raines]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Ella Raines
Context triple: [Phantom Lady, stars, Ella Raines]
  • A. Ella Raines chosen
    Ella Raines was an American film and television actress of the 1940s and 1950s, known for her roles in film noir and dramatic features.
  • B. Laraine Day
    Laraine Day was an American film and television actress best known for her roles in 1940s Hollywood films and as the female lead in Alfred Hitchcock’s thriller "Foreign Correspondent."
  • C. Janis Paige
    Janis Paige was an American film, stage, and television actress and singer best known for her work in 1940s–1950s Hollywood musicals and Broadway productions such as "The Pajama Game."
  • D. Gloria DeHaven
    Gloria DeHaven was an American actress and singer best known for her roles in classic Hollywood musicals of the 1940s and 1950s.
  • E. Ava Starr
    Ava Starr is the Marvel Cinematic Universe character known as Ghost, a quantumly unstable antagonist-turned-antihero who appears in "Ant-Man and the Wasp."
  • 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_69e0b4b3a6e08190ae663701f50fab8e completed April 16, 2026, 10:06 a.m.
NER Named-entity recognition batch_69e6a06504b48190b3f1defdc23a47d5 completed April 20, 2026, 9:53 p.m.
Created at: April 16, 2026, 11:37 a.m.