Triple

T19358852
Position Surface form Disambiguated ID Type / Status
Subject Tony Rome E484222 entity
Predicate starring P1507 FINISHED
Object Richard Conte NE NERFINISHED

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: Richard Conte | Statement: [Tony Rome, starring, Richard Conte]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Richard Conte
Context triple: [Tony Rome, starring, Richard Conte]
  • A. Richard Conte chosen
    Richard Conte was an American film and television actor best known for his roles in classic crime dramas and film noir, including "The Godfather" and "Thieves' Highway."
  • B. Frank Giustra
    Frank Giustra is a Canadian businessman and philanthropist best known as the founder of Lionsgate Entertainment and for his extensive work in the mining and film industries.
  • C. Arthur Caan
    Arthur Caan is the son of the late American actor James Caan, known for his iconic roles in films such as "The Godfather."
  • D. Vincent DeGiorgio
    Vincent DeGiorgio is a Canadian music producer, songwriter, and music executive known for his work in pop and dance music internationally.
  • E. Richard Crenna
    Richard Crenna was an American actor and director known for his roles in films such as the "Rambo" series and numerous television shows including "The Real McCoys."
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 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_69d8e8d305088190ad13571532aa454c completed April 10, 2026, 12:10 p.m.
NER Named-entity recognition batch_69e6190a1ec88190ba6d2d45174dc85a completed April 20, 2026, 12:16 p.m.
Created at: April 10, 2026, 1:34 p.m.