Triple

T8074377
Position Surface form Disambiguated ID Type / Status
Subject Marie-George Buffet E188455 entity
Predicate familyName P18 FINISHED
Object Buffet E432449 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: Buffet | Statement: [Marie-George Buffet, familyName, Buffet]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Buffet
Context triple: [Marie-George Buffet, familyName, Buffet]
  • A. Buffet chosen
    Buffet is a style of meal service in which a variety of dishes are laid out on a table or sideboard for guests to serve themselves.
  • B. The Buffet
    The Buffet is a 2015 studio album by American R&B singer R. Kelly that blends contemporary R&B with elements of soul, hip hop, and pop.
  • C. Summit Suite Buffet
    Summit Suite Buffet is a revolving dining restaurant located near the top of the Skylon Tower in Niagara Falls, offering panoramic views alongside buffet-style meals.
  • D. Banket
    Banket is a small mining and farming town located in Zimbabwe's Mashonaland West Province.
  • E. Diner
    Diner is a 1982 American coming-of-age comedy-drama film directed by Barry Levinson that follows a group of friends reuniting in 1959 Baltimore as they navigate adulthood, relationships, and changing times.
  • 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_69ca82b50c708190863f661d438e68df completed March 30, 2026, 2:03 p.m.
NER Named-entity recognition batch_69cb404a98408190b6c8eecb95ad086d completed March 31, 2026, 3:32 a.m.
NED1 Entity disambiguation (via context triple) batch_69cc63f000308190a55379f8bf67f0cd completed April 1, 2026, 12:16 a.m.
Created at: March 30, 2026, 5:27 p.m.