Triple

T10002311
Position Surface form Disambiguated ID Type / Status
Subject Yeongdo Island E197355 entity
Predicate hasViewOf P854 FINISHED
Object Busan skyline E154500 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 skyline | Statement: [Yeongdo Island, hasViewOf, Busan skyline]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Busan skyline
Context triple: [Yeongdo Island, hasViewOf, Busan skyline]
  • A. Busan city center
    Busan city center is the bustling downtown core of Busan, South Korea, known for its dense shopping streets, markets, and entertainment districts.
  • B. Busan waterfront chosen
    The Busan waterfront is a bustling coastal area in South Korea’s second-largest city, known for its busy port, seafood markets, and scenic seaside promenades.
  • C. Ulsan city center
    Ulsan city center is the main commercial and administrative hub of Ulsan, South Korea, characterized by dense urban development, shopping districts, and business facilities.
  • D. Busan Tower
    Busan Tower is a prominent observation tower in Busan, South Korea, offering panoramic views of the city and its harbor.
  • E. Busan, South Korea
    Busan, South Korea is the country’s second-largest city and a major coastal hub known for its busy port, beaches, and international film festival.
  • 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_69d25857f0988190aebe8951f7c0ef86 completed April 5, 2026, 12:40 p.m.
Created at: March 30, 2026, 8:51 p.m.