Triple

T17609771
Position Surface form Disambiguated ID Type / Status
Subject Sir John Coke E428936 entity
Predicate familyName P18 FINISHED
Object Coke NE NERFINISHED

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: Coke | Statement: [Sir John Coke, familyName, Coke]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Coke
Context triple: [Sir John Coke, familyName, Coke]
  • A. Coke chosen
    Coke is an English aristocratic family name historically associated with prominent peers, politicians, and landowners in Britain.
  • B. Chero-Cola
    Chero-Cola was the early 20th-century soft drink brand that later evolved into the better-known RC Cola.
  • C. P-Cola
    P-Cola is a common shorthand nickname for the city of Pensacola in the Florida Panhandle.
  • D. Buzz Cola
    Buzz Cola is a fictional soft drink brand from the animated television series "The Simpsons," often depicted as a popular but comically unhealthy beverage in Springfield.
  • E. Diet Dr Pepper
    Diet Dr Pepper is a sugar-free, low-calorie version of the Dr Pepper soft drink that maintains a similar distinctive flavor using artificial sweeteners.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 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_69d889e1c6148190ba76241e74688f8b completed April 10, 2026, 5:25 a.m.
NER Named-entity recognition batch_69e46c4e6ba48190804e113983e7c704 completed April 19, 2026, 5:46 a.m.
Created at: April 10, 2026, 5:51 a.m.