Triple
T8235735
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Busan Central Bus Terminal |
E192399
|
entity |
| Predicate | connectsTo |
P845
|
FINISHED |
| Object | Mokpo |
E613689
|
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: Mokpo | Statement: [Busan Central Bus Terminal, connectsTo, Mokpo]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Mokpo Context triple: [Busan Central Bus Terminal, connectsTo, Mokpo]
-
A.
Mokpo
chosen
Mokpo is a coastal city in South Jeolla Province, South Korea, known as a regional transportation hub and gateway to numerous nearby islands.
-
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.
Gwangyang
Gwangyang is an industrial port city in South Korea known for its major steelworks complex and scenic coastal and mountainous landscapes.
-
D.
Gunsan
Gunsan is a coastal city in North Jeolla Province, South Korea, known for its port, industrial facilities, and longstanding association with nearby military air operations.
-
E.
Yeosu
Yeosu is a coastal city in South Jeolla Province, South Korea, known for its scenic archipelago, maritime industry, and role as host of the 2012 World Expo.
- 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_69ca82dc8f148190a2c75a98501a7b91 |
completed | March 30, 2026, 2:04 p.m. |
| NER | Named-entity recognition | batch_69cb782a5e18819096235679f5a644a8 |
completed | March 31, 2026, 7:30 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69cef2b985888190a692f52cf5b93a80 |
completed | April 2, 2026, 10:50 p.m. |
Created at: March 30, 2026, 5:46 p.m.