Triple

T21688897
Position Surface form Disambiguated ID Type / Status
Subject Marchesa E535304 entity
Predicate coFoundedBy P3263 FINISHED
Object Keren Craig 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: Keren Craig | Statement: [Marchesa, coFoundedBy, Keren Craig]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Keren Craig
Context triple: [Marchesa, coFoundedBy, Keren Craig]
  • A. Keren Craig chosen
    Keren Craig is a British fashion designer best known as the co-founder of the luxury womenswear label Marchesa alongside Georgina Chapman.
  • B. Kerri Browitt Caviezel
    Kerri Browitt Caviezel is an American English teacher and former college basketball player best known as the longtime wife of actor Jim Caviezel.
  • C. Claire Jackman
    Claire Jackman is a fictional character portrayed by actress Gina Bellman, known from her work in British television and film.
  • D. Tania Gibson
    Tania Gibson is a New Zealand local government politician who serves as the mayor of the Grey District on the South Island’s West Coast.
  • E. Suzanne Mackie
    Suzanne Mackie is a British television and film producer known for her work on acclaimed projects such as "The Crown" and other high-profile UK dramas.
  • 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_69e0c469b6ec8190aee4cadd1527db91 completed April 16, 2026, 11:13 a.m.
NER Named-entity recognition batch_69ef96cd51d481908df67e4f69826b06 completed April 27, 2026, 5:03 p.m.
Created at: April 16, 2026, 6:44 p.m.