Triple

T16190213
Position Surface form Disambiguated ID Type / Status
Subject Brian Madison E392915 entity
Predicate owns P347 FINISHED
Object Madison Hotels E1199554 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: Madison Hotels | Statement: [Brian Madison, owns, Madison Hotels]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Madison Hotels
Context triple: [Brian Madison, owns, Madison Hotels]
  • A. Madison Hotels chosen
    Madison Hotels is a hospitality company that operates and manages a portfolio of hotel properties.
  • B. Grand America Hotels & Resorts
    Grand America Hotels & Resorts is a luxury hotel and resort company in the United States known for operating upscale properties such as The Grand America Hotel in Salt Lake City.
  • C. Kimpton Hotels
    Kimpton Hotels is a boutique hotel chain known for its stylish, design-focused properties and personalized guest experiences, primarily operating in urban locations across the United States and beyond.
  • D. Biltmore Hotels
    Biltmore Hotels is a historic American luxury hotel brand known for developing and operating grand, landmark properties in major cities during the early 20th century.
  • E. Sheraton
    Sheraton is a global upscale hotel brand known for its full-service accommodations and business-friendly amenities.
  • 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_69d87f1e49ac8190a311b54d32990576 completed April 10, 2026, 4:39 a.m.
NER Named-entity recognition batch_69e222d4ab8081909a02e5138b29b83b completed April 17, 2026, 12:08 p.m.
NED1 Entity disambiguation (via context triple) batch_6a00078bbc388190b3fb793556ddd75a completed May 10, 2026, 4:20 a.m.
Created at: April 10, 2026, 5:02 a.m.