Triple

T15722332
Position Surface form Disambiguated ID Type / Status
Subject Harold Hecht E381127 entity
Predicate employer P7 FINISHED
Object Norma Productions E404731 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: Norma Productions | Statement: [Harold Hecht, employer, Norma Productions]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Norma Productions
Context triple: [Harold Hecht, employer, Norma Productions]
  • A. Norma Productions chosen
    Norma Productions was an American film production company best known for producing classic mid-20th-century movies such as "Birdman of Alcatraz."
  • B. Norman Rosemont Productions
    Norman Rosemont Productions was a television and film production company best known for producing high-quality adaptations of classic literary works.
  • C. Albert Productions
    Albert Productions is an Australian independent record label and production company best known for discovering and nurturing rock bands such as AC/DC.
  • D. Davis-Panzer Productions
    Davis-Panzer Productions is a film and television production company best known for creating and producing the Highlander franchise.
  • E. Sunflower Productions
    Sunflower Productions is a film production company known for producing the historical drama "The New World."
  • 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_69d86d9bf930819082b30cf6d169297c completed April 10, 2026, 3:25 a.m.
NER Named-entity recognition batch_69e04fb0b51081908e652ec4992296fa completed April 16, 2026, 2:55 a.m.
NED1 Entity disambiguation (via context triple) batch_69ff876759288190b263cbea00fdaba4 completed May 9, 2026, 7:13 p.m.
Created at: April 10, 2026, 4:45 a.m.