Triple

T20740621
Position Surface form Disambiguated ID Type / Status
Subject Finding Graceland E510428 entity
Predicate starred P5563 FINISHED
Object Harvey Keitel 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: Harvey Keitel | Statement: [Finding Graceland, starred, Harvey Keitel]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Harvey Keitel
Context triple: [Finding Graceland, starred, Harvey Keitel]
  • A. Harvey Keitel chosen
    Harvey Keitel is an American actor known for his intense, often morally complex roles in films by directors like Martin Scorsese and Quentin Tarantino, including classics such as "Mean Streets," "Taxi Driver," and "Reservoir Dogs."
  • B. Robert De Niro
    Robert De Niro is an acclaimed American actor and producer renowned for his intense, transformative performances in films such as "Taxi Driver," "Raging Bull," and "The Godfather Part II."
  • C. De Niro
    De Niro is a prominent Italian-American surname most famously associated with acclaimed actor Robert De Niro and his family.
  • D. Ned Beatty
    Ned Beatty was an acclaimed American character actor known for his powerful supporting roles in films such as "Deliverance," "Network," and "Superman."
  • E. Peter Strauss
    Peter Strauss is an American actor best known for his work in television miniseries and films, including prominent roles in dramas throughout the 1970s and 1980s.
  • 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_69e0b4c845e88190b4c5f3ae79291182 completed April 16, 2026, 10:07 a.m.
NER Named-entity recognition batch_69e6c20e76ac8190985203b2c17aca14 completed April 21, 2026, 12:17 a.m.
Created at: April 16, 2026, 12:32 p.m.