Triple

T20856278
Position Surface form Disambiguated ID Type / Status
Subject Manchester Regional Arena E513489 entity
Predicate locatedIn P40 FINISHED
Object Sportcity 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: Sportcity | Statement: [Manchester Regional Arena, locatedIn, Sportcity]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Sportcity
Context triple: [Manchester Regional Arena, locatedIn, Sportcity]
  • A. Sportcity complex chosen
    Sportcity complex is a major sports and leisure district in east Manchester that includes multiple venues and facilities developed around the City of Manchester Stadium.
  • B. KL Sports City
    KL Sports City is a major integrated sports and entertainment complex in Kuala Lumpur, Malaysia, featuring multiple stadiums and facilities for national and international events.
  • C. Entertainment City
    Entertainment City is a major integrated resort and gaming complex in Metro Manila known for its large casinos, luxury hotels, and entertainment venues.
  • D. Hub City
    Hub City is the nickname of Crestview, Florida, reflecting its role as a central crossroads and regional center in the Florida Panhandle.
  • E. Hub City
    Hub City is a common nickname for Moncton, a major transportation and commercial center in New Brunswick, Canada.
  • 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_69e0b4f5b01081909452f654d2fc3f50 completed April 16, 2026, 10:07 a.m.
NER Named-entity recognition batch_69e6c3a81ac4819084a07625b8ed4ec5 completed April 21, 2026, 12:24 a.m.
Created at: April 16, 2026, 12:44 p.m.