Triple

T10390997
Position Surface form Disambiguated ID Type / Status
Subject Man on a Ledge E244890 entity
Predicate productionCompany P490 FINISHED
Object Di Bonaventura Pictures E322044 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: Di Bonaventura Pictures | Statement: [Man on a Ledge, productionCompany, Di Bonaventura Pictures]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Di Bonaventura Pictures
Context triple: [Man on a Ledge, productionCompany, Di Bonaventura Pictures]
  • A. Di Bonaventura Pictures chosen
    Di Bonaventura Pictures is an American film and television production company founded by producer Lorenzo di Bonaventura, known for backing large-scale action and genre franchises.
  • B. Di Novi Pictures
    Di Novi Pictures is an American film production company founded by producer Denise Di Novi, known for its work on character-driven dramas and literary adaptations.
  • C. Passion Pictures
    Passion Pictures is a renowned independent production company, particularly acclaimed for its documentary and animated films.
  • D. Myriad Pictures
    Myriad Pictures is an independent film production and distribution company known for handling a range of arthouse and specialty films.
  • E. Benaroya Pictures
    Benaroya Pictures is an independent film production company known for financing and producing a range of critically acclaimed and commercially successful feature films.
  • 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_69d381b5116081908d85227bab6d3c0c completed April 6, 2026, 9:49 a.m.
NER Named-entity recognition batch_69d4e9b4f7d08190bcb16d3b4c8f22ad completed April 7, 2026, 11:25 a.m.
NED1 Entity disambiguation (via context triple) batch_69d795b9974c819087340adc3622279e completed April 9, 2026, 12:04 p.m.
Created at: April 6, 2026, 12:06 p.m.