Triple

T20771512
Position Surface form Disambiguated ID Type / Status
Subject Katy Brand E511247 entity
Predicate name P16 FINISHED
Object Katy Brand 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: Katy Brand | Statement: [Katy Brand, name, Katy Brand]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Katy Brand
Context triple: [Katy Brand, name, Katy Brand]
  • A. Katy Brand chosen
    Katy Brand is a British comedian, actress, and writer known for her sketch show "Katy Brand's Big Ass Show" and numerous film, television, and stage appearances.
  • B. Katy Brandwood
    Katy Brandwood is best known as the wife of the late British comedian and radio personality Jeremy Hardy.
  • C. Katy Cavanagh
    Katy Cavanagh is a British actress best known for her role as Julie Carp on the long-running soap opera "Coronation Street."
  • D. Katy O’Brian
    Katy O’Brian is an American actress and martial artist known for her physically intense and action-oriented roles in film and television.
  • E. Katie Morgan
    Katie Morgan is a struggling single mother in the British social-realist film "I, Daniel Blake," whose experiences highlight the failures of the welfare system.
  • 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_69e0b4ca01148190ac018e57e0cab46f completed April 16, 2026, 10:07 a.m.
NER Named-entity recognition batch_69e6c266f4b48190891c0db3e322bb23 completed April 21, 2026, 12:18 a.m.
Created at: April 16, 2026, 12:36 p.m.