Triple

T17890137
Position Surface form Disambiguated ID Type / Status
Subject Barefoot E447292 entity
Predicate starring P1507 FINISHED
Object Kate Burton 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 Burton | Statement: [Barefoot, starring, Kate Burton]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Kate Burton
Context triple: [Barefoot, starring, Kate Burton]
  • A. Kate Burton chosen
    Kate Burton is a British-American actress known for her work on stage and in television series such as "Grey's Anatomy" and "Scandal."
  • B. Rebecca Gibney
    Rebecca Gibney is a New Zealand-born Australian actress known for her prominent roles in film and television, including acclaimed Australian dramas and comedies.
  • C. Lara Pulver
    Lara Pulver is a British actress known for her roles in television series such as "Sherlock" and "Spooks," as well as various film and stage productions.
  • D. Helen Gibson
    Helen Gibson was a pioneering American silent film actress and stunt performer, best known as one of early cinema’s first professional stuntwomen.
  • E. Patricia Hopkins
    Patricia Hopkins is a British architect known for her influential modern designs and as a co-founder of the firm Hopkins Architects.
  • 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_69d8b9f59bd48190a6fc925a855b8bac completed April 10, 2026, 8:51 a.m.
NER Named-entity recognition batch_69e49d7828b481909b645fceb37a7ca3 completed April 19, 2026, 9:16 a.m.
Created at: April 10, 2026, 10:18 a.m.