Triple

T20186027
Position Surface form Disambiguated ID Type / Status
Subject Arrie Clark E492863 entity
Predicate alternateName P39 FINISHED
Object Kate Barker 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 Barker | Statement: [Arrie Clark, alternateName, Kate Barker]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Kate Barker
Context triple: [Arrie Clark, alternateName, Kate Barker]
  • A. Kate Barker
    Kate Barker, better known as Ma Barker, was an American criminal figure infamous for leading the Barker–Karpis gang during the early 20th century.
  • B. Kate Barker chosen
    Kate Barker is a British economist known for her work on housing and planning policy, including influential reviews for the UK government and service on the Bank of England’s Monetary Policy Committee.
  • C. Sophie Hunter
    Sophie Hunter is a British theatre and opera director, playwright, and former actress known for her avant-garde stage work and marriage to actor Benedict Cumberbatch.
  • D. Jennifer Bourke
    Jennifer Bourke is known as the spouse of actor Robert Shaw.
  • E. Nichola Burley
    Nichola Burley is a British actress known for her roles in film and television dramas, particularly in contemporary UK cinema.
  • 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_69da6268a034819081cbd9ea5a1c9475 completed April 11, 2026, 3:02 p.m.
NER Named-entity recognition batch_69e668f2c03c819096336462f59dba91 completed April 20, 2026, 5:57 p.m.
Created at: April 11, 2026, 11:36 p.m.