Triple
T8146509
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Busan Harbor Bridge |
E190223
|
entity |
| Predicate | KoreanName |
P17869
|
FINISHED |
| Object | 부산항대교 |
E710061
|
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: 부산항대교 | Statement: [Busan Harbor Bridge, KoreanName, 부산항대교]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: 부산항대교 Context triple: [Busan Harbor Bridge, KoreanName, 부산항대교]
-
A.
광안대교
광안대교는 부산 광안리해수욕장과 마린시티 일대를 잇는 대한민국의 대표적인 해상 복층 교량이자 야경 명소이다.
-
B.
남항대교
chosen
남항대교는 부산 남항을 가로지르며 서구와 영도구를 연결하는 해상 교량이다.
-
C.
Incheon Bridge
Incheon Bridge is a major cable-stayed bridge in South Korea that links Incheon International Airport on Yeongjong Island with the mainland city of Incheon, serving as a key transportation and logistics route.
-
D.
구포대교
구포대교는 부산광역시 북구와 인근 지역을 연결하며 낙동강을 가로지르는 주요 도로 교량이다.
-
E.
Seongsu Bridge
Seongsu Bridge is a major road bridge in Seoul, South Korea, known both for its role in connecting districts across the Han River and for its infamous 1994 collapse and subsequent reconstruction.
- 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_69ca82be7ba8819087de0147e9292c83 |
completed | March 30, 2026, 2:03 p.m. |
| NER | Named-entity recognition | batch_69cb447d6b1881908ff3fa25af6b4e80 |
completed | March 31, 2026, 3:50 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69cd679a353c8190abe30eb7db13c072 |
completed | April 1, 2026, 6:44 p.m. |
Created at: March 30, 2026, 5:36 p.m.