Triple

T14691344
Position Surface form Disambiguated ID Type / Status
Subject Army of the Dead E345041 entity
Predicate stars P1956 FINISHED
Object Ella Purnell E1016938 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: Ella Purnell | Statement: [Army of the Dead, stars, Ella Purnell]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Ella Purnell
Context triple: [Army of the Dead, stars, Ella Purnell]
  • A. Ella Purnell chosen
    Ella Purnell is a British actress known for roles in films like "Miss Peregrine's Home for Peculiar Children" and series such as "Yellowjackets" and "Fallout."
  • B. Ella Logan
    Ella Logan was a Scottish-born American singer and actress best known for originating the role of Sharon McLonergan in the Broadway musical "Finian's Rainbow."
  • C. Ella Rice
    Ella Rice is an American academic and former spouse of filmmaker George Lucas, known for her work in education and her connection to the early life of the Star Wars creator.
  • D. Ella Rice
    Ella Rice was the first wife of American business magnate and aviator Howard Hughes, whom he married in the 1920s before his rise to great fame.
  • E. Ella Leonard Norris
    Ella Leonard Norris was the wife of longtime Nebraska U.S. Senator and progressive Republican reformer George W. Norris.
  • 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_69d822e34b348190ada4d1cdb6c7c226 completed April 9, 2026, 10:06 p.m.
NER Named-entity recognition batch_69deb585d46c81908d6964130914cec4 completed April 14, 2026, 9:45 p.m.
NED1 Entity disambiguation (via context triple) batch_69fdfb807af081908dd56caf3d06550f completed May 8, 2026, 3:04 p.m.
Created at: April 10, 2026, 1:28 a.m.