Triple

T19960653
Position Surface form Disambiguated ID Type / Status
Subject Angela Ahrendts E479803 entity
Predicate employer P7 FINISHED
Object Liz Claiborne 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: Liz Claiborne | Statement: [Angela Ahrendts, employer, Liz Claiborne]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Liz Claiborne
Context triple: [Angela Ahrendts, employer, Liz Claiborne]
  • A. Liz Claiborne chosen
    Liz Claiborne was a pioneering American fashion designer and businesswoman who founded the Liz Claiborne Inc. brand, becoming one of the first female CEOs of a Fortune 500 company.
  • B. Ralph Lauren Corporation
    Ralph Lauren Corporation is a global American fashion and lifestyle company known for its premium apparel, accessories, home furnishings, and iconic Polo brand.
  • C. Donna Karan
    Donna Karan is an influential American fashion designer best known for founding the DKNY label and redefining modern women’s workwear with her sleek, versatile designs.
  • D. Ann Taylor
    Ann Taylor was a daughter of U.S. President Zachary Taylor and the sister of Sarah Knox Taylor, belonging to the prominent 19th-century Taylor family.
  • E. Ann Taylor
    Ann Taylor was the wife of James Patton Preston, an early 19th-century American politician and Governor of Virginia.
  • 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_69d8e523c19881909f9197037200dde6 completed April 10, 2026, 11:55 a.m.
NER Named-entity recognition batch_69e65af4520c81909986a47289ba801e completed April 20, 2026, 4:57 p.m.
Created at: April 10, 2026, 1:54 p.m.