Triple

T22957435
Position Surface form Disambiguated ID Type / Status
Subject Dead Again E570798 entity
Predicate starring P1507 FINISHED
Object Emma Thompson 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: Emma Thompson | Statement: [Dead Again, starring, Emma Thompson]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Emma Thompson
Context triple: [Dead Again, starring, Emma Thompson]
  • A. Emma Thompson chosen
    Emma Thompson is an acclaimed British actress and screenwriter known for her Oscar-winning performances and adaptations in films such as "Howards End" and "Sense and Sensibility."
  • B. Joanna Lumley
    Joanna Lumley is a British actress, presenter, and former model best known for her iconic role as Patsy Stone in the television series "Absolutely Fabulous."
  • C. Anne Boulting
    Anne Boulting was the wife of British film director and producer John Boulting, associated with the mid-20th-century British cinema scene.
  • D. Fiona Brice
    Fiona Brice is a British composer, arranger, and multi-instrumentalist known for her orchestral collaborations with alternative and indie rock artists.
  • E. Dawn French
    Dawn French is a British comedian and actress best known as one half of the comedy duo French and Saunders and for her acclaimed television work in shows such as "The Vicar of Dibley."
  • 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_69e245b212a88190b5259caf51606084 completed April 17, 2026, 2:37 p.m.
NER Named-entity recognition batch_69f181f21e588190a5a88a15c1b55dea completed April 29, 2026, 3:58 a.m.
Created at: April 17, 2026, 3:47 p.m.