Triple

T9301361
Position Surface form Disambiguated ID Type / Status
Subject House of Fraser E223768 entity
Predicate formerName P65 FINISHED
Object Frasers E137851 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: Frasers | Statement: [House of Fraser, formerName, Frasers]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Frasers
Context triple: [House of Fraser, formerName, Frasers]
  • A. Frasers chosen
    Frasers is a British department store chain offering a wide range of fashion, beauty, and home products.
  • B. House of Fraser department store
    House of Fraser department store is a major British retail chain known for its large multi-brand department stores offering fashion, beauty, and homeware.
  • C. Nicholsons
    Nicholsons is a variant form of the surname Nicholson, typically used as a family name.
  • D. FBR House
    FBR House is the main administrative headquarters of Pakistan’s Federal Board of Revenue, where the country’s federal tax and revenue policies are managed and overseen.
  • E. Frederick's of Hollywood
    Frederick's of Hollywood is an American lingerie retailer known for its provocative designs and prominent presence in popular culture and fashion advertising.
  • 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_69ca8423edb08190bc0c91287a484768 completed March 30, 2026, 2:09 p.m.
NER Named-entity recognition batch_69cd08d1d954819098be177addafa406 completed April 1, 2026, noon
NED1 Entity disambiguation (via context triple) batch_69d0b26302608190a59f3ed0694ce6d9 completed April 4, 2026, 6:40 a.m.
Created at: March 30, 2026, 7:36 p.m.