Triple

T14877729
Position Surface form Disambiguated ID Type / Status
Subject Claude Berri E349909 entity
Predicate founded P104 FINISHED
Object Films A2 E663445 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: Films A2 | Statement: [Claude Berri, founded, Films A2]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Films A2
Context triple: [Claude Berri, founded, Films A2]
  • A. Films A2 chosen
    Films A2 is a French film production company known for backing notable works such as the Academy Award–winning war satire "Black and White in Color."
  • B. Type A Films
    Type A Films is a film production company established by actress and producer Reese Witherspoon to develop character-driven, often female-led projects.
  • C. Subafilms
    Subafilms was a film production company associated with The Beatles, involved in producing several of their cinematic projects during the 1960s.
  • D. ARRAY Filmworks
    ARRAY Filmworks is a film and television production company founded by filmmaker Ava DuVernay, known for championing diverse voices and inclusive storytelling.
  • E. A-2
    The A-2 is a major Spanish motorway that connects Madrid with northeastern regions such as Zaragoza and Barcelona, forming part of the country’s primary eastward transport corridor.
  • 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_69d822ee4f408190b6ac3b2fa434f0df completed April 9, 2026, 10:06 p.m.
NER Named-entity recognition batch_69ded5e4e4448190a8796573bc6d1069 completed April 15, 2026, 12:03 a.m.
NED1 Entity disambiguation (via context triple) batch_69fe6b54ad7c819082575245da07e358 completed May 8, 2026, 11:01 p.m.
Created at: April 10, 2026, 1:55 a.m.