Triple

T20453032
Position Surface form Disambiguated ID Type / Status
Subject Do Revenge E501702 entity
Predicate portrays P264 FINISHED
Object Drea Torres 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: Drea Torres | Statement: [Do Revenge, portrays, Drea Torres]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Drea Torres
Context triple: [Do Revenge, portrays, Drea Torres]
  • A. Drea Torres chosen
    Drea Torres is the ambitious, status-conscious high school student and main protagonist of the dark teen comedy film "Do Revenge," portrayed by Camila Mendes.
  • B. Rebecca Rodriguez
    Rebecca Rodriguez is a film editor known for her work on the family action-adventure movie "Spy Kids: All the Time in the World."
  • C. Bridgette Rios
    Bridgette Rios is a musician known for contributing guest performances to Steve Vai’s album "The Story of Light."
  • D. Ramona Vega
    Ramona Vega is a charismatic, savvy veteran stripper and ringleader in the film "Hustlers," who masterminds a scheme to swindle wealthy Wall Street clients.
  • E. Taura Stinson
    Taura Stinson is an American songwriter and author known for her work across pop, R&B, and film soundtracks, collaborating with prominent artists and contributing to award-nominated projects.
  • 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_69e0b4ac0a1c81908845d0f8a56abce8 completed April 16, 2026, 10:06 a.m.
NER Named-entity recognition batch_69e68d039af08190827bf765b50515a8 completed April 20, 2026, 8:30 p.m.
Created at: April 16, 2026, 11:32 a.m.