Triple

T10002307
Position Surface form Disambiguated ID Type / Status
Subject Yeongdo Island E197355 entity
Predicate adjacentTo P224 FINISHED
Object Nam-gu, Busan E633469 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: Nam-gu, Busan | Statement: [Yeongdo Island, adjacentTo, Nam-gu, Busan]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Nam-gu, Busan
Context triple: [Yeongdo Island, adjacentTo, Nam-gu, Busan]
  • A. Nam-gu, Busan chosen
    Nam-gu, Busan is a coastal district in the south-central part of Busan, South Korea, known for its residential neighborhoods, universities, and views over the city and harbor.
  • B. Nam-gu, Ulsan
    Nam-gu, Ulsan is a coastal district in the metropolitan city of Ulsan, South Korea, known for its industrial facilities and maritime heritage.
  • C. Buk-gu, Busan
    Buk-gu, Busan is a northern district of Busan, South Korea, known as a largely residential and industrial area within the metropolitan city.
  • D. Jung-gu, Busan
    Jung-gu, Busan is a central district of Busan, South Korea, known for its historic downtown area, bustling commercial streets, and major shopping and cultural attractions.
  • E. Changwon
    Changwon is a major industrial and administrative city in South Gyeongsang Province, South Korea, known for its planned urban layout and role as a regional government and manufacturing hub.
  • 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_69ca82f3b61c81908ecc2c1c96dbc2e4 completed March 30, 2026, 2:04 p.m.
NER Named-entity recognition batch_69cdcc9078788190a4e75dd7ff830c63 completed April 2, 2026, 1:55 a.m.
NED1 Entity disambiguation (via context triple) batch_69f49c59538081909102a6954f564e46 completed May 1, 2026, 12:28 p.m.
Created at: March 30, 2026, 8:51 p.m.