Triple
T6774665
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ulsan-gwangyeoksi |
E155125
|
entity |
| Predicate | hasPort |
P35
|
FINISHED |
| Object | Port of Ulsan |
E611840
|
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: Port of Ulsan | Statement: [Ulsan-gwangyeoksi, hasPort, Port of Ulsan]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Port of Ulsan Context triple: [Ulsan-gwangyeoksi, hasPort, Port of Ulsan]
-
A.
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.
-
B.
Port of Busan New Port
Port of Busan New Port is a major deep-water container terminal complex in South Korea that serves as a key transshipment hub in the Asia-Pacific region.
-
C.
Jeju Port
Jeju Port is a major maritime gateway on South Korea’s Jeju Island, serving as a key hub for passenger ferries, cargo shipping, and regional tourism.
-
D.
Jangsaengpo Port
chosen
Jangsaengpo Port is a coastal port area in Ulsan, South Korea, historically known for its whaling industry and now a hub for marine tourism.
-
E.
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.
- 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_69c68812ef7c819099369f51febb725c |
completed | March 27, 2026, 1:37 p.m. |
| NER | Named-entity recognition | batch_69c6d24ddaf08190baffbff991eeb458 |
completed | March 27, 2026, 6:54 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c7582b5a0c819085e6b8d07d6ab2f7 |
completed | March 28, 2026, 4:25 a.m. |
Created at: March 27, 2026, 2:13 p.m.