Triple

T18996003
Position Surface form Disambiguated ID Type / Status
Subject Rebecca Da Costa E464814 entity
Predicate coStarredWith P14987 FINISHED
Object Robert De Niro 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: Robert De Niro | Statement: [Rebecca Da Costa, coStarredWith, Robert De Niro]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Robert De Niro
Context triple: [Rebecca Da Costa, coStarredWith, Robert De Niro]
  • A. Robert De Niro chosen
    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."
  • B. De Niro
    De Niro is a prominent Italian-American surname most famously associated with acclaimed actor Robert De Niro and his family.
  • C. Al Pacino
    Al Pacino is an acclaimed American actor known for his intense, charismatic performances in classic films such as The Godfather series, Scarface, and Scent of a Woman.
  • D. Elliot De Niro
    Elliot De Niro is one of the children of acclaimed American actor Robert De Niro.
  • E. Harvey Keitel
    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."
  • 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_69d8dd01a56c81909694a128c66b21d7 completed April 10, 2026, 11:20 a.m.
NER Named-entity recognition batch_69e5d6819f8c81908bbf0448baf7e34b completed April 20, 2026, 7:32 a.m.
Created at: April 10, 2026, 12:01 p.m.