Triple

T14435913
Position Surface form Disambiguated ID Type / Status
Subject Marriott Bonvoy E357959 entity
Predicate coversBrand P1500 FINISHED
Object Westin E866620 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: Westin | Statement: [Marriott Bonvoy, coversBrand, Westin]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Westin
Context triple: [Marriott Bonvoy, coversBrand, Westin]
  • A. Westin chosen
    Westin is an upscale hotel and resort brand known for its wellness-focused amenities, including signature Heavenly Beds and fitness-oriented services.
  • B. Hilton
    Hilton is a village and civil parish in South Derbyshire, England, known for its rapid modern expansion and residential developments.
  • C. Hilton
    Hilton is a global hospitality company that operates a worldwide portfolio of hotels and resorts across multiple brands.
  • D. Hilton
    Hilton is an inner-western suburb of Adelaide in South Australia, known for its proximity to the city centre and mixed residential–commercial character.
  • E. Hyatt
    Hyatt is a surname most notably associated with Alpheus Hyatt, an American zoologist and paleontologist known for his work on evolutionary theory and cephalopods.
  • 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_69d8279402a88190821ffa39ae15bccf completed April 9, 2026, 10:26 p.m.
NER Named-entity recognition batch_69de9148cf4481909082cc91b2f76218 completed April 14, 2026, 7:11 p.m.
NED1 Entity disambiguation (via context triple) batch_69fd6d84fd888190b05dcf9191bae337 completed May 8, 2026, 4:58 a.m.
Created at: April 10, 2026, 1:18 a.m.