Triple

T2899254
Position Surface form Disambiguated ID Type / Status
Subject Jon Kortajarena E62615 entity
Predicate hasWorkedAsFaceOfBrand P29719 FINISHED
Object Balmain E40457 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: Balmain | Statement: [Jon Kortajarena, hasWorkedAsFaceOfBrand, Balmain]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Balmain
Context triple: [Jon Kortajarena, hasWorkedAsFaceOfBrand, Balmain]
  • A. Balmain
    Balmain is a historic inner-west suburb of Sydney, Australia, known for its waterfront location on Sydney Harbour, preserved Victorian architecture, and vibrant pub and café culture.
  • B. Balmain chosen
    Balmain is a French luxury fashion house renowned for its opulent, sharply tailored designs and influential presence on international runways.
  • C. Balenciaga
    Balenciaga is a luxury French fashion house renowned for its avant-garde, architectural designs and influential role in high fashion.
  • D. Givenchy
    Givenchy is a renowned French luxury fashion and perfume house known for its haute couture, ready-to-wear collections, and iconic collaborations with celebrities and models.
  • E. Kenzo
    Kenzo is a Japanese masculine given name borne by various notable figures in fields such as architecture, fashion, and entertainment.
  • 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_69ab4c3e070c8190b78d3d2c005876dd completed March 6, 2026, 9:50 p.m.
NER Named-entity recognition batch_69abe0ad7bbc8190822738baa6935b74 completed March 7, 2026, 8:24 a.m.
NED1 Entity disambiguation (via context triple) batch_69b0318c544881909f6aabfb2d25e724 completed March 10, 2026, 2:58 p.m.
Created at: March 6, 2026, 10:10 p.m.