Triple

T21688884
Position Surface form Disambiguated ID Type / Status
Subject Keren Craig E535304 entity
Predicate employer P7 FINISHED
Object Marchesa 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: Marchesa | Statement: [Keren Craig, employer, Marchesa]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Marchesa
Context triple: [Keren Craig, employer, Marchesa]
  • A. Marchesa chosen
    Marchesa is a luxury fashion label renowned for its ornate, red-carpet-ready eveningwear and bridal gowns.
  • B. Marchesa
    Marchesa is the Italian noble title traditionally used to designate a woman holding the rank of marquess.
  • C. Nina Ricci
    Nina Ricci is a French luxury fashion house renowned for its elegant haute couture, ready-to-wear collections, and iconic fragrances.
  • D. Denis of Paris
    Denis of Paris is a 3rd-century Christian martyr and bishop, venerated as the patron saint of Paris and traditionally regarded as one of the city’s earliest evangelizers.
  • E. Kumpire Dior
    Kumpire Dior is a high mountain peak in the remote Batura Muztagh subrange of the Karakoram in northern Pakistan.
  • 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.