Triple

T8318573
Position Surface form Disambiguated ID Type / Status
Subject Dunkin' E194768 entity
Predicate competitor P1375 FINISHED
Object Krispy Kreme E125070 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: Krispy Kreme | Statement: [Dunkin', competitor, Krispy Kreme]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Krispy Kreme
Context triple: [Dunkin', competitor, Krispy Kreme]
  • A. Krispy Kreme chosen
    Krispy Kreme is an American doughnut company and coffeehouse chain best known for its Original Glazed doughnuts and signature “Hot Now” sign.
  • B. Dunkin'
    Dunkin' is a major American coffee and baked goods chain best known for its donuts and wide variety of coffee beverages.
  • C. Panera Bread
    Panera Bread is a popular American fast-casual restaurant and bakery chain known for its soups, salads, sandwiches, and freshly baked bread.
  • D. Hardee
    Hardee is a surname most notably associated with William J. Hardee, a 19th-century United States Army officer and Confederate general during the American Civil War.
  • E. Baskin-Robbins
    Baskin-Robbins is a global ice cream and frozen dessert chain famous for its “31 flavors” concept and wide variety of creative ice cream offerings.
  • 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_69ca82e6e2648190a31eaf6f4f757b2a completed March 30, 2026, 2:04 p.m.
NER Named-entity recognition batch_69cb7f648e10819081ad1fed870b2b86 completed March 31, 2026, 8:01 a.m.
NED1 Entity disambiguation (via context triple) batch_69cde78855908190a87a0d3456c0e8ef completed April 2, 2026, 3:50 a.m.
Created at: March 30, 2026, 5:55 p.m.