Triple

T13292924
Position Surface form Disambiguated ID Type / Status
Subject Chiayi City E316602 entity
Predicate hasSisterCity P919 FINISHED
Object Gumi, South Korea E336613 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: Gumi, South Korea | Statement: [Chiayi City, hasSisterCity, Gumi, South Korea]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Gumi, South Korea
Context triple: [Chiayi City, hasSisterCity, Gumi, South Korea]
  • A. Gumi, South Korea chosen
    Gumi, South Korea is an industrial city in North Gyeongsang Province known as a major electronics manufacturing hub and home to several large technology companies.
  • B. Gunsan, South Korea
    Gunsan, South Korea is a coastal industrial city in North Jeolla Province known for its port, manufacturing facilities, and role as a regional transportation hub.
  • C. Bupyong, South Korea
    Bupyong, South Korea is an industrial district in Incheon known for its major automotive manufacturing facilities and dense urban development.
  • D. Osan, South Korea
    Osan is a city in Gyeonggi Province, South Korea, known for its proximity to Osan Air Base and its role as a transportation and commercial hub south of Seoul.
  • E. Ulsan, South Korea
    Ulsan, South Korea is a major industrial port city known as a global hub for automobile and ship manufacturing.
  • 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_69d806b349908190a9a61dd9323bf153 completed April 9, 2026, 8:06 p.m.
NER Named-entity recognition batch_69d99078bcf0819083195fb556bcacb2 completed April 11, 2026, 12:06 a.m.
NED1 Entity disambiguation (via context triple) batch_69f716d6dc988190ab7183089113237f completed May 3, 2026, 9:35 a.m.
Created at: April 9, 2026, 9:27 p.m.