Triple

T10002282
Position Surface form Disambiguated ID Type / Status
Subject Yeongdo Island E197355 entity
Predicate connectsTo P845 FINISHED
Object Busan mainland E285640 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: Busan mainland | Statement: [Yeongdo Island, connectsTo, Busan mainland]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Busan mainland
Context triple: [Yeongdo Island, connectsTo, Busan mainland]
  • A. Nam-gu, Busan
    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. Gangjin
    Gangjin is a coastal county and town in South Jeolla Province, South Korea, known for its historic celadon pottery kilns and scenic rural landscapes.
  • C. Busan North Port area
    The Busan North Port area is a key maritime and redevelopment district within Busan’s waterfront, encompassing port facilities, logistics hubs, and emerging urban spaces.
  • D. Mokpo
    Mokpo is a coastal city in South Jeolla Province, South Korea, known as a regional transportation hub and gateway to numerous nearby islands.
  • E. Busan Jung District chosen
    Busan Jung District is a central urban district of Busan, South Korea, known for its historic downtown area, bustling commercial streets, and major shopping and cultural attractions.
  • 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_69f489b62b808190a3fc89e73e8ae2f7 completed May 1, 2026, 11:08 a.m.
Created at: March 30, 2026, 8:51 p.m.