Triple

T20559028
Position Surface form Disambiguated ID Type / Status
Subject Passionada E504794 entity
Predicate starring P1507 FINISHED
Object Theresa Russell 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: Theresa Russell | Statement: [Passionada, starring, Theresa Russell]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Theresa Russell
Context triple: [Passionada, starring, Theresa Russell]
  • A. Theresa Russell chosen
    Theresa Russell is an American actress known for her intense and often provocative performances in films such as "Bad Timing," "Black Widow," and "Track 29."
  • B. Theresa Randle
    Theresa Randle is an American actress known for her roles in films such as "Bad Boys," "Spawn," and "Girl 6."
  • C. Theresa Russo
    Theresa Russo is a central character in the Disney Channel series "Wizards of Waverly Place," known as the non-magical, practical mother of the wizard Russo siblings.
  • D. Theresa Hanson
    Theresa Hanson is a Canadian university sports administrator who serves as the athletic director for Simon Fraser University's Red Leafs athletic program.
  • E. Theresa Galloway
    Theresa Galloway is known as the wife of American war correspondent and author Joseph L. Galloway.
  • 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_69e0b4b6587c8190aee63dc7cff244ea completed April 16, 2026, 10:06 a.m.
NER Named-entity recognition batch_69e6a5e178648190910795bae5422e50 completed April 20, 2026, 10:17 p.m.
Created at: April 16, 2026, 11:38 a.m.