Triple

T11203136
Position Surface form Disambiguated ID Type / Status
Subject Edie Knightley Righton E265090 entity
Predicate mother P120 FINISHED
Object Keira Knightley E53444 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: Keira Knightley | Statement: [Edie Knightley Righton, mother, Keira Knightley]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Keira Knightley
Context triple: [Edie Knightley Righton, mother, Keira Knightley]
  • A. Keira Knightley chosen
    Keira Knightley is an English actress known for her roles in period dramas and major film franchises such as "Pirates of the Caribbean" and "Pride & Prejudice."
  • B. Beth Winslet
    Beth Winslet is a British actress and the younger sister of acclaimed film star Kate Winslet.
  • C. Gemma Arterton
    Gemma Arterton is an English actress known for her roles in films such as "St Trinian's," "Quantum of Solace," and "Prince of Persia: The Sands of Time."
  • D. Emily Watson
    Emily Watson is an acclaimed English actress known for her powerful performances in films such as "Breaking the Waves," "Hilary and Jackie," and "Punch-Drunk Love."
  • E. Sophie Fiennes
    Sophie Fiennes is a British film director and producer known for her innovative documentaries and collaborations with artists and philosophers.
  • 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_69d6aa9eb9248190b20211772621b4bc completed April 8, 2026, 7:21 p.m.
NER Named-entity recognition batch_69d7e8d355c481908fc3d555b596314d completed April 9, 2026, 5:58 p.m.
NED1 Entity disambiguation (via context triple) batch_69e4cc2ec5348190b66a3cc5779aa327 completed April 19, 2026, 12:35 p.m.
Created at: April 8, 2026, 9:29 p.m.