Triple

T8582372
Position Surface form Disambiguated ID Type / Status
Subject Andy Harries E203213 entity
Predicate employer P7 FINISHED
Object Left Bank Pictures E114993 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: Left Bank Pictures | Statement: [Andy Harries, employer, Left Bank Pictures]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Left Bank Pictures
Context triple: [Andy Harries, employer, Left Bank Pictures]
  • A. Left Bank Pictures chosen
    Left Bank Pictures is a British television and film production company known for creating high-profile, critically acclaimed dramas including the royal series "The Crown."
  • B. Greenpoint Films
    Greenpoint Films is a film production company best known for producing the acclaimed period drama "Enchanted April."
  • C. Parklane Pictures
    Parklane Pictures was a mid-20th-century American film production company best known for producing the classic 1955 film noir "Kiss Me Deadly."
  • D. Beyond Films
    Beyond Films is an Australian film distribution and production company known for handling a range of independent and international titles.
  • E. Washington Square Films
    Washington Square Films is an American independent film production company known for backing critically acclaimed, character-driven movies.
  • 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_69ca8329bb7c8190a63c643730839103 completed March 30, 2026, 2:05 p.m.
NER Named-entity recognition batch_69cbeb1d0edc8190b4495935275252f3 completed March 31, 2026, 3:41 p.m.
NED1 Entity disambiguation (via context triple) batch_69cea89e4658819090cc6e94e934670b completed April 2, 2026, 5:34 p.m.
Created at: March 30, 2026, 6:22 p.m.