Triple

T8458082
Position Surface form Disambiguated ID Type / Status
Subject Roger Corman E199970 entity
Predicate familyName P18 FINISHED
Object Corman E199970 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: Corman | Statement: [Roger Corman, familyName, Corman]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Corman
Context triple: [Roger Corman, familyName, Corman]
  • A. Cis Corman
    Cis Corman was an American casting director and film producer known for her long-time collaboration with Barbra Streisand on several major films.
  • B. Roger Corman chosen
    Roger Corman is an American filmmaker and producer renowned for his low-budget cult classics and for launching the careers of numerous major Hollywood directors and actors.
  • C. Vidor
    Vidor is a surname most notably associated with King Vidor, an influential American film director of the early to mid-20th century.
  • D. Le Fanu
    Le Fanu is the surname of the Anglo-Irish family best known for producing the Victorian Gothic writer Sheridan Le Fanu.
  • E. William Castle
    William Castle was an American film director and producer best known for his low-budget horror movies and inventive, gimmick-driven promotional stunts in the 1950s and 1960s.
  • 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_69ca8318231881908fd1bc1c4d45d286 completed March 30, 2026, 2:05 p.m.
NER Named-entity recognition batch_69cbe49064f881909391d565b97e9886 completed March 31, 2026, 3:13 p.m.
NED1 Entity disambiguation (via context triple) batch_69ce1dea01c481909496ebfca4e9916e completed April 2, 2026, 7:42 a.m.
Created at: March 30, 2026, 6:10 p.m.