Triple

T11761902
Position Surface form Disambiguated ID Type / Status
Subject New York Marriott Marquis E279676 entity
Predicate chain P58694 FINISHED
Object Marriott E246350 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: Marriott | Statement: [New York Marriott Marquis, chain, Marriott]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Marriott
Context triple: [New York Marriott Marquis, chain, Marriott]
  • A. Hilton
    Hilton is a village and civil parish in South Derbyshire, England, known for its rapid modern expansion and residential developments.
  • B. Marriotts
    Marriotts is likely a person or family name commemorated by having Marriotts Stadium named in their honor.
  • C. Marriott International chosen
    Marriott International is a global hospitality company that owns, manages, and franchises a wide portfolio of hotel and lodging brands worldwide.
  • D. Westin
    Westin is an upscale hotel and resort brand known for its wellness-focused amenities, including signature Heavenly Beds and fitness-oriented services.
  • E. JW Marriott
    JW Marriott is a luxury hotel brand within Marriott International known for its upscale accommodations, refined service, and business-oriented amenities in major cities and resort destinations worldwide.
  • 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_69d6ab01d2688190ad8ed6bda487eaa5 completed April 8, 2026, 7:22 p.m.
NER Named-entity recognition batch_69d8a52386708190b744746a2db37495 completed April 10, 2026, 7:22 a.m.
NED1 Entity disambiguation (via context triple) batch_69f1309f25a88190b0acaf7d9be6ae59 completed April 28, 2026, 10:11 p.m.
Created at: April 8, 2026, 9:41 p.m.