Triple

T5111502
Position Surface form Disambiguated ID Type / Status
Subject Whitbread Children's Book of the Year E115222 entity
Predicate sponsor P67 FINISHED
Object Costa Coffee E85138 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: Costa Coffee | Statement: [Whitbread Children's Book of the Year, sponsor, Costa Coffee]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Costa Coffee
Context triple: [Whitbread Children's Book of the Year, sponsor, Costa Coffee]
  • A. Costa Coffee chosen
    Costa Coffee is a major British coffeehouse chain known for its espresso-based drinks and café-style food, operating thousands of outlets worldwide.
  • B. Caffè Nero
    Caffè Nero is a European-style coffeehouse chain known for its Italian-inspired espresso drinks and relaxed café atmosphere.
  • C. Starbucks
    Starbucks is a global coffeehouse chain and coffee roastery brand known for its specialty coffee drinks and widespread presence in cities around the world.
  • D. McCafé
    McCafé is McDonald's in-house coffeehouse-style chain offering specialty coffee drinks, pastries, and café-style food items.
  • E. Dunkin'
    Dunkin' is a major American coffee and baked goods chain best known for its donuts and wide variety of coffee beverages.
  • 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_69bd4441d1648190a54a533895041987 completed March 20, 2026, 12:57 p.m.
NER Named-entity recognition batch_69bd75ca57e881908242def2a032902e completed March 20, 2026, 4:28 p.m.
NED1 Entity disambiguation (via context triple) batch_69bebaaa394c8190bd93cdf57475a5b6 completed March 21, 2026, 3:35 p.m.
Created at: March 20, 2026, 1:41 p.m.