Triple

T4591284
Position Surface form Disambiguated ID Type / Status
Subject Sofia Richie E103493 entity
Predicate hasWorkedWithBrand P42926 FINISHED
Object Michael Kors E40456 NE FINISHED

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: Michael Kors | Statement: [Sofia Richie, hasWorkedWithBrand, Michael Kors]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Michael Kors
Context triple: [Sofia Richie, hasWorkedWithBrand, Michael Kors]
  • A. Michael Kors chosen
    Michael Kors is an American fashion designer best known for his eponymous luxury brand specializing in ready-to-wear clothing, accessories, and handbags.
  • B. Kenneth Cole
    Kenneth Cole is an American fashion designer and entrepreneur best known for his eponymous footwear and lifestyle brand and socially conscious advertising campaigns.
  • C. Nicole Miller
    Nicole Miller is an American fashion designer renowned for her modern, feminine womenswear and bold use of color and print.
  • D. David Lauren
    David Lauren is an American businessman and executive at the fashion company Ralph Lauren, founded by his father Ralph Lauren.
  • E. Kate Spade
    Kate Spade was an American fashion designer and businesswoman best known for her colorful, playful handbags and for founding the Kate Spade New York brand.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (3 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_69bd43dccaf08190aa89e9991a289719 completed March 20, 2026, 12:55 p.m.
NER Named-entity recognition batch_69bd6234e8108190b985270b9ddd1f3a completed March 20, 2026, 3:05 p.m.
NED1 Entity disambiguation (via context triple) batch_69bde0cdc7e8819088758c1d6d8e866d completed March 21, 2026, 12:05 a.m.
Created at: March 20, 2026, 1:11 p.m.