Triple

T17652265
Position Surface form Disambiguated ID Type / Status
Subject The Widow E429523 entity
Predicate starring P1507 FINISHED
Object Kate Beckinsale 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: Kate Beckinsale | Statement: [The Widow, starring, Kate Beckinsale]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Kate Beckinsale
Context triple: [The Widow, starring, Kate Beckinsale]
  • A. Kate Beckinsale chosen
    Kate Beckinsale is an English actress known for her versatile film career, including prominent roles in action, drama, and comedy films such as the Underworld series and various Hollywood productions.
  • B. Lara Flynn Boyle
    Lara Flynn Boyle is an American actress best known for her role as Donna Hayward in the television series "Twin Peaks" and for her work in films and other TV dramas throughout the 1990s and 2000s.
  • C. Catherine Bell
    Catherine Bell is an American actress best known for her role as Lieutenant Colonel Sarah "Mac" MacKenzie on the television series JAG.
  • D. Megan Boone
    Megan Boone is an American actress best known for her leading role as FBI profiler Elizabeth Keen on the television series "The Blacklist."
  • E. Lynne Brimley
    Lynne Brimley is best known as the wife of American character actor Wilford Brimley.
  • 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_69d889e2c2608190b762e76d9b2262f1 completed April 10, 2026, 5:25 a.m.
NER Named-entity recognition batch_69e46e3e0ae481908382570f802d8144 completed April 19, 2026, 5:55 a.m.
Created at: April 10, 2026, 6:05 a.m.