Triple

T4441003
Position Surface form Disambiguated ID Type / Status
Subject True Lies E95769 entity
Predicate starring P1507 FINISHED
Object Eliza Dushku E299060 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: Eliza Dushku | Statement: [True Lies, starring, Eliza Dushku]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Eliza Dushku
Context triple: [True Lies, starring, Eliza Dushku]
  • A. Eliza Dushku chosen
    Eliza Dushku is an American actress best known for her roles in films like "Bring It On" and TV series such as "Buffy the Vampire Slayer" and "Dollhouse."
  • B. Heather Lind
    Heather Lind is an American actress known for her work in film, television, and theater, including roles in projects like the indie comedy-drama "Mistress America."
  • C. Shannyn Sossamon
    Shannyn Sossamon is an American actress and musician known for her roles in early 2000s films such as "A Knight's Tale" and various independent and genre movies.
  • D. Veronica Moore
    Veronica Moore is a powerhouse Broadway star character portrayed by Jennifer Hudson in the musical drama television series "Smash."
  • E. Tara Reid
    Tara Reid is an American actress best known for her roles in films like "American Pie" and "The Big Lebowski," as well as the "Sharknado" television movie series.
  • 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_69b3453ea2b48190a26f154b3b8fece5 completed March 12, 2026, 10:59 p.m.
NER Named-entity recognition batch_69b355ac05e081908411089c05fc36bd completed March 13, 2026, 12:09 a.m.
NED1 Entity disambiguation (via context triple) batch_69b65f34df20819090767fe4c577be87 completed March 15, 2026, 7:26 a.m.
Created at: March 12, 2026, 11:32 p.m.