Triple
T17772575
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ryanggang Province |
E443676
|
entity |
| Predicate | containsCity |
P294
|
FINISHED |
| Object | Hyesan |
—
|
NE NERFINISHED |
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: Hyesan | Statement: [Ryanggang Province, containsCity, Hyesan]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Hyesan Context triple: [Ryanggang Province, containsCity, Hyesan]
-
A.
Hyesan
chosen
Hyesan is a major city in northern North Korea, located on the border with China along the Yalu River and serving as an important regional administrative and transport hub.
-
B.
Taegwan
Taegwan is a town and county-level city in North Pyongan Province in northwestern North Korea.
-
C.
Phyongwon
Phyongwon is a city in North Korea known as an administrative and agricultural center within North Pyongan Province.
-
D.
Ko Ri
Ko Ri is one of the small islands that make up Thailand’s Surin Islands archipelago in the Andaman Sea.
-
E.
Sŏngjin
Sŏngjin is the former name of Kim Chaek City, an industrial port city on North Korea’s east coast.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69d8b9ef17708190bdf7e2adbf14ddc2 |
completed | April 10, 2026, 8:50 a.m. |
| NER | Named-entity recognition | batch_69e4871a2130819081743ae89dddc64b |
completed | April 19, 2026, 7:41 a.m. |
Created at: April 10, 2026, 10:11 a.m.