Triple

T8278774
Position Surface form Disambiguated ID Type / Status
Subject Goodfellas E193611 entity
Predicate castMember P1668 FINISHED
Object Catherine Scorsese E238633 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: Catherine Scorsese | Statement: [Goodfellas, castMember, Catherine Scorsese]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Catherine Scorsese
Context triple: [Goodfellas, castMember, Catherine Scorsese]
  • A. Catherine Scorsese chosen
    Catherine Scorsese was an Italian-American actress best known for her frequent appearances in her son Martin Scorsese’s films, often portraying warm, talkative New York mothers.
  • B. Francesca Scorsese
    Francesca Scorsese is an American actress and filmmaker, known for her roles in independent films and for being the daughter of acclaimed director Martin Scorsese.
  • C. Marc Coppola
    Marc Coppola is an American actor and radio DJ, and a member of the Coppola filmmaking family.
  • D. Domenica Cameron-Scorsese
    Domenica Cameron-Scorsese is an American actress and filmmaker, and the daughter of acclaimed director Martin Scorsese.
  • E. Gia Coppola
    Gia Coppola is an American film director, screenwriter, and photographer known for her work in independent cinema and as a member of the Coppola filmmaking family.
  • 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_69ca82e217a48190880695635c44b2ed completed March 30, 2026, 2:04 p.m.
NER Named-entity recognition batch_69cb79ebb6b88190bc777b8bd72fcdbc completed March 31, 2026, 7:38 a.m.
NED1 Entity disambiguation (via context triple) batch_69cd6863c22c8190b888a23bb9005712 completed April 1, 2026, 6:48 p.m.
Created at: March 30, 2026, 5:51 p.m.