Triple

T17887321
Position Surface form Disambiguated ID Type / Status
Subject Earth-Two E447230 entity
Predicate hasCity P316 FINISHED
Object Keystone City 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: Keystone City | Statement: [Earth-Two, hasCity, Keystone City]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Keystone City
Context triple: [Earth-Two, hasCity, Keystone City]
  • A. Keystone City chosen
    Keystone City is a fictional American city in DC Comics, best known as one of the primary home cities of the superhero The Flash.
  • B. Fort Morgan
    Fort Morgan is a historic 19th-century masonry fort on Mobile Bay in Alabama, best known for its role in the American Civil War, particularly the Battle of Mobile Bay.
  • C. The Wheat City
    The Wheat City is the nickname of Brandon, Manitoba, reflecting its historical role as a major center for grain production and agricultural trade on the Canadian Prairies.
  • D. Keystone, Colorado
    Keystone, Colorado is a mountain community in Summit County known primarily as the base village and service hub for the nearby Keystone Resort ski area.
  • E. Sedalia
    Sedalia is a small town in Guilford County, North Carolina, known for its historic African American educational institution, the Palmer Memorial Institute.
  • 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_69d8b9f59bd48190a6fc925a855b8bac completed April 10, 2026, 8:51 a.m.
NER Named-entity recognition batch_69e49c14c4348190bb77712d9eae1d51 completed April 19, 2026, 9:10 a.m.
Created at: April 10, 2026, 10:18 a.m.