Triple

T23140249
Position Surface form Disambiguated ID Type / Status
Subject Beastly E577440 entity
Predicate starring P1507 FINISHED
Object Mary-Kate Olsen 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: Mary-Kate Olsen | Statement: [Beastly, starring, Mary-Kate Olsen]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Mary-Kate Olsen
Context triple: [Beastly, starring, Mary-Kate Olsen]
  • A. Mary-Kate Olsen chosen
    Mary-Kate Olsen is an American actress and fashion designer who rose to fame as a child star alongside her twin sister Ashley in television and film before transitioning into a successful career in high-end fashion.
  • B. Mary Kate Schellhardt
    Mary Kate Schellhardt is an American actress best known for her role as Ellen Grape in the 1993 film "What's Eating Gilbert Grape."
  • C. Mary Kate Danaher
    Mary Kate Danaher is the strong-willed, passionate Irish heroine of the classic John Ford film "The Quiet Man," portrayed by Maureen O'Hara.
  • D. Ashley Olsen
    Ashley Olsen is an American fashion designer, businesswoman, and former child actress who rose to fame starring alongside her twin sister Mary-Kate in television and film projects.
  • E. Kaitlin Doubleday
    Kaitlin Doubleday is an American actress known for her roles in film and television, including prominent parts on the series "Empire" and "Nashville."
  • 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_69e245f8e6248190ba3d58e068b4dccb completed April 17, 2026, 2:38 p.m.
NER Named-entity recognition batch_69f18ec922b481908084eee6a95aef83 completed April 29, 2026, 4:53 a.m.
Created at: April 17, 2026, 4 p.m.