Triple

T14806536
Position Surface form Disambiguated ID Type / Status
Subject With a Friend Like Harry... E348051 entity
Predicate productionCompany P490 FINISHED
Object Diaphana Films E259896 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: Diaphana Films | Statement: [With a Friend Like Harry..., productionCompany, Diaphana Films]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Diaphana Films
Context triple: [With a Friend Like Harry..., productionCompany, Diaphana Films]
  • A. Diaphana Films chosen
    Diaphana Films is a French film distribution and production company known for handling acclaimed international and auteur cinema.
  • B. Cinelou Films
    Cinelou Films is an independent American film production company known for producing character-driven dramas such as the 2014 film "Cake."
  • C. Valoria Films
    Valoria Films is a film distribution company known for handling the release of various international and independent movies.
  • D. Aquarius Films
    Aquarius Films is an Australian film and television production company known for creating distinctive, character-driven screen content for both local and international audiences.
  • E. Ombra Films
    Ombra Films is a film production company known for working on action and thriller movies, including the crime thriller "Run All Night."
  • 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_69d822ea8b7c819097dfadf3d45545e6 completed April 9, 2026, 10:06 p.m.
NER Named-entity recognition batch_69decf33b6a08190ab6a4cfeda2cc09c completed April 14, 2026, 11:35 p.m.
NED1 Entity disambiguation (via context triple) batch_69fe3893c760819094ce1d63478a39ce completed May 8, 2026, 7:25 p.m.
Created at: April 10, 2026, 1:40 a.m.