Triple

T21957800
Position Surface form Disambiguated ID Type / Status
Subject The TV Set E542236 entity
Predicate starring P1507 FINISHED
Object Lucy Davis 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: Lucy Davis | Statement: [The TV Set, starring, Lucy Davis]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Lucy Davis
Context triple: [The TV Set, starring, Lucy Davis]
  • A. Lucy Davis chosen
    Lucy Davis is a British actress best known for her comedic and character roles in film and television, including her appearance in the 2017 superhero film "Wonder Woman."
  • B. Lucy Marlow
    Lucy Marlow was an American film and television actress of the 1950s, known for supporting roles in Hollywood productions including the musical drama "A Star Is Born."
  • C. Lucy Deakins
    Lucy Deakins is an American former actress best known for her lead role in the 1986 fantasy drama film "The Boy Who Could Fly."
  • D. Lucy Ashton
    Lucy Ashton is the tragic heroine of Sir Walter Scott's novel "The Bride of Lammermoor," whose ill-fated love and forced marriage lead to madness and death.
  • E. Lucy Fletcher
    Lucy Fletcher is the daughter of Ian Fletcher.
  • 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_69e0c47fab1081908dc74a6545dbb051 completed April 16, 2026, 11:14 a.m.
NER Named-entity recognition batch_69f1244108948190a08e6966e55c4acd completed April 28, 2026, 9:18 p.m.
Created at: April 16, 2026, 8 p.m.