Triple

T2486933
Position Surface form Disambiguated ID Type / Status
Subject Marriage Story E55947 entity
Predicate starring P1507 FINISHED
Object Ray Liotta E69965 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 Liotta | Statement: [Marriage Story, starring, Ray Liotta]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Ray Liotta
Context triple: [Marriage Story, starring, Ray Liotta]
  • A. Ray Liotta chosen
    Ray Liotta was an American actor best known for his intense, charismatic performances in films such as "Goodfellas," "Field of Dreams," and numerous crime and drama roles.
  • B. Emilio Estevez
    Emilio Estevez is an American actor, director, and writer known for films like "The Breakfast Club," "St. Elmo's Fire," and "The Mighty Ducks" series.
  • C. Joe Estevez
    Joe Estevez is an American character actor known for his extensive work in low-budget and independent films and for being the younger brother of actor Martin Sheen.
  • D. Paul Wahlberg
    Paul Wahlberg is an American chef and restaurateur best known as the co-founder of the Wahlburgers restaurant chain and brother of actors Mark and Donnie Wahlberg.
  • E. Matt Dillon
    Matt Dillon is an American actor known for his versatile performances in films ranging from 1980s teen dramas like "The Outsiders" to acclaimed roles in movies such as "Drugstore Cowboy" and "Crash."
  • 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_69ab49e670a88190b928e08302381710 completed March 6, 2026, 9:40 p.m.
NER Named-entity recognition batch_69abd1782ca081909645164a6acf0ea0 completed March 7, 2026, 7:19 a.m.
NED1 Entity disambiguation (via context triple) batch_69af17bca6f88190a63672fb3372f0be completed March 9, 2026, 6:55 p.m.
Created at: March 6, 2026, 9:45 p.m.