Triple

T956900
Position Surface form Disambiguated ID Type / Status
Subject The Irishman E20643 entity
Predicate starring P1507 FINISHED
Object Ray Romano E60897 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: Ray Romano | Statement: [The Irishman, starring, Ray Romano]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Ray Romano
Context triple: [The Irishman, starring, Ray Romano]
  • A. Ray Romano chosen
    Ray Romano is an American stand-up comedian and actor best known for creating and starring in the hit sitcom "Everybody Loves Raymond."
  • B. Jim Gaffigan
    Jim Gaffigan is an American stand-up comedian and actor known for his observational, family-friendly humor and roles in both film and television.
  • C. Glenn Howerton
    Glenn Howerton is an American actor, writer, and producer best known for co-creating and starring as Dennis Reynolds on the dark comedy series "It's Always Sunny in Philadelphia."
  • D. Rick Leary
    Rick Leary is a Canadian public transit executive who serves as the chief executive officer of the Toronto Transit Commission, overseeing the city’s bus, streetcar, and subway operations.
  • E. Michael Ian Black
    Michael Ian Black is an American comedian, actor, writer, and director known for his work on "The State," "Stella," and numerous stand-up and television appearances.
  • 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_69a493b21f2881908132dcf45dcd2f36 completed March 1, 2026, 7:29 p.m.
NER Named-entity recognition batch_69a4b3f981bc819098125554eeeb6375 completed March 1, 2026, 9:47 p.m.
NED1 Entity disambiguation (via context triple) batch_69ac17016be0819097207669eae17490 completed March 7, 2026, 12:16 p.m.
Created at: March 1, 2026, 7:40 p.m.