Triple

T20029425
Position Surface form Disambiguated ID Type / Status
Subject American Ultra E495080 entity
Predicate mainCharacter P1183 FINISHED
Object Phoebe Larson 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: Phoebe Larson | Statement: [American Ultra, mainCharacter, Phoebe Larson]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Phoebe Larson
Context triple: [American Ultra, mainCharacter, Phoebe Larson]
  • A. Hannah Murray
    Hannah Murray is an English actress best known for her roles as Cassie Ainsworth in the TV series "Skins" and Gilly in "Game of Thrones."
  • B. Haley Hudson chosen
    Haley Hudson is an American actress best known for her roles in horror and supernatural films and television series.
  • C. Amanda Hedlund
    Amanda Hedlund is known as the sister of American actor and singer Garrett Hedlund.
  • D. Emma Kenney
    Emma Kenney is an American actress best known for playing Debbie Gallagher on the U.S. version of the television series "Shameless."
  • E. Madelaine Petsch
    Madelaine Petsch is an American actress best known for playing Cheryl Blossom on the television series "Riverdale."
  • 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_69da626bfd288190aa5d65098b6433ae completed April 11, 2026, 3:02 p.m.
NER Named-entity recognition batch_69e662908df081909a6c8ccf0dd90fff completed April 20, 2026, 5:29 p.m.
Created at: April 11, 2026, 3:36 p.m.