Triple

T14021225
Position Surface form Disambiguated ID Type / Status
Subject Thom E337333 entity
Predicate hasNotableBearer P458 FINISHED
Object Thom Browne E838511 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: Thom Browne | Statement: [Thom, hasNotableBearer, Thom Browne]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Thom Browne
Context triple: [Thom, hasNotableBearer, Thom Browne]
  • A. Thom Browne chosen
    Thom Browne is an American fashion designer renowned for his avant-garde, meticulously tailored menswear and his influential eponymous label.
  • B. Kenneth Jay Lane
    Kenneth Jay Lane is a renowned American jewelry designer celebrated for his glamorous, high-quality costume jewelry favored by celebrities and socialites.
  • C. Rick Owens
    Rick Owens is an American fashion designer renowned for his avant-garde, gothic-influenced aesthetic and influential luxury menswear and womenswear label.
  • D. Gareth Pugh
    Gareth Pugh is a British fashion designer known for his avant-garde, sculptural creations and experimental use of materials on the runway.
  • E. Pablo Proenza
    Pablo Proenza is a film editor best known for his work on Michael Moore’s documentary "Where to Invade Next."
  • 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_69d81c6543a48190bd5ba93d7419e797 completed April 9, 2026, 9:38 p.m.
NER Named-entity recognition batch_69de2f3c7cd88190b236382058581740 completed April 14, 2026, 12:12 p.m.
NED1 Entity disambiguation (via context triple) batch_69fbc32f78dc8190bd357d179cbaa5bc completed May 6, 2026, 10:39 p.m.
Created at: April 9, 2026, 10:19 p.m.