Triple

T3065654
Position Surface form Disambiguated ID Type / Status
Subject Lion E62098 entity
Predicate screenwriter P2831 FINISHED
Object Luke Davies E296234 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: Luke Davies | Statement: [Lion, screenwriter, Luke Davies]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Luke Davies
Context triple: [Lion, screenwriter, Luke Davies]
  • A. Luke Davies chosen
    Luke Davies is an Australian poet, novelist, and screenwriter known for adapting acclaimed films such as "Lion" and "News of the World."
  • B. Darren Eales
    Darren Eales is a British football executive known for serving as president of Major League Soccer club Atlanta United FC, where he helped build the expansion team into a successful franchise.
  • C. Luke Brattan
    Luke Brattan is an Australian professional footballer and midfielder known for his playmaking ability in the A-League.
  • D. Will Firth
    Will Firth is the son of English actor Colin Firth and is known primarily for his connection to his father's prominent film career.
  • E. Adam Gough
    Adam Gough is a British film editor known for his work on acclaimed films such as "Da 5 Bloods" and "Roma."
  • 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_69ad85793e5c8190a358049bc4a98d8c completed March 8, 2026, 2:19 p.m.
NER Named-entity recognition batch_69ada0fc01dc81908fbdf7c1ef73afe4 completed March 8, 2026, 4:17 p.m.
NED1 Entity disambiguation (via context triple) batch_69b28ded6588819093abd0c0c6158579 completed March 12, 2026, 9:57 a.m.
Created at: March 8, 2026, 3:02 p.m.