Triple

T8552108
Position Surface form Disambiguated ID Type / Status
Subject Art of Fighting E202467 entity
Predicate setting P1957 FINISHED
Object South Town E741476 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: South Town | Statement: [Art of Fighting, setting, South Town]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: South Town
Context triple: [Art of Fighting, setting, South Town]
  • A. South Town chosen
    South Town is a fictional, crime-ridden American metropolis that serves as the primary backdrop for SNK’s Fatal Fury and related fighting game series.
  • B. B-Town
    B-Town is a common nickname for Bloomington, Indiana, a vibrant Midwestern college city best known as the home of Indiana University.
  • C. Mob Town
    Mob Town is a historic nickname for the city of Baltimore, reflecting its long-standing reputation for civil unrest and rowdy public gatherings in the 19th century.
  • D. Cross Town
    Cross Town is a residential neighbourhood within the town of Knutsford in Cheshire, England.
  • E. Outer City
    The Outer City was the extensive outer urban area surrounding the central core of Dadu, the Yuan dynasty capital later known as Beijing.
  • 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_69ca832610e08190b3b6c6cd2c250255 completed March 30, 2026, 2:05 p.m.
NER Named-entity recognition batch_69cbe886fb788190a73e7c76c4f86409 completed March 31, 2026, 3:30 p.m.
NED1 Entity disambiguation (via context triple) batch_69ce892efdf8819093c966bd8f6c8065 completed April 2, 2026, 3:20 p.m.
Created at: March 30, 2026, 6:19 p.m.