Triple

T23435940
Position Surface form Disambiguated ID Type / Status
Subject Wando County E563460 entity
Predicate administrativeCenter P1474 FINISHED
Object Wando-eup 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: Wando-eup | Statement: [Wando County, administrativeCenter, Wando-eup]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Wando-eup
Context triple: [Wando County, administrativeCenter, Wando-eup]
  • A. Wando-eup chosen
    Wando-eup is the main urban and administrative center of Wando County in South Jeolla Province, South Korea, located on Wando Island.
  • B. Geumwang-eup
    Geumwang-eup is a town-level administrative division in Eumseong County, located in North Chungcheong Province, South Korea.
  • C. Eonyang-eup
    Eonyang-eup is a town in Ulju County, Ulsan, South Korea, known as a local administrative and commercial hub for the surrounding region.
  • D. Ongjin-eup
    Ongjin-eup is the main town and administrative center of Ongjin County in North Korea’s South Hwanghae Province.
  • E. Beomseo-eup
    Beomseo-eup is a town-level administrative division located within Ulju County in Ulsan, South Korea.
  • 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_69e24553980c8190bb66a2ae0bdab125 completed April 17, 2026, 2:36 p.m.
NER Named-entity recognition batch_69f1a5dbdf248190a09e971f2718d01f completed April 29, 2026, 6:31 a.m.
Created at: April 17, 2026, 5:50 p.m.