Triple
T10002306
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Yeongdo Island |
E197355
|
entity |
| Predicate | adjacentTo |
P224
|
FINISHED |
| Object | Busan Port |
E756553
|
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 Port | Statement: [Yeongdo Island, adjacentTo, Busan Port]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Busan Port Context triple: [Yeongdo Island, adjacentTo, Busan Port]
-
A.
Busan South Port
Busan South Port is a major harbor area in Busan, South Korea, serving as an important hub for maritime trade and transportation.
-
B.
Busan North Port
Busan North Port is a major harbor area in Busan, South Korea, serving as one of the city’s key maritime and logistics hubs.
-
C.
Incheon Port
Incheon Port is a major seaport in Incheon, South Korea, serving as a key gateway for international trade and maritime transport near the capital Seoul.
-
D.
Port of Busan
chosen
The Port of Busan is South Korea’s largest and busiest seaport, serving as a major global hub for container shipping and passenger ferries in Northeast Asia.
-
E.
Gunsan Port
Gunsan Port is a major seaport in Gunsan, South Korea, serving as an important hub for regional trade and maritime transport.
- 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_69d2820063f48190886619fe26b0cc94 |
completed | April 5, 2026, 3:38 p.m. |
Created at: March 30, 2026, 8:51 p.m.