Triple
T17571918
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Gwangmyeong |
E427958
|
entity |
| Predicate | hasRomanization |
P2508
|
FINISHED |
| Object | Kwangmyŏng-si |
—
|
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: Kwangmyŏng-si | Statement: [Gwangmyeong, hasRomanization, Kwangmyŏng-si]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Kwangmyŏng-si Context triple: [Gwangmyeong, hasRomanization, Kwangmyŏng-si]
-
A.
Kŏje-si
Kŏje-si is the McCune–Reischauer romanization of Geoje, a city in South Gyeongsang Province, South Korea, known for its shipbuilding industry and scenic coastal landscapes.
-
B.
Gwangmyeong
chosen
Gwangmyeong is a city in South Korea known for its proximity to Seoul and attractions like the Gwangmyeong Cave, a former mine turned cultural and tourism complex.
-
C.
Kyongsong
Kyongsong is a coastal town and county-level city in northeastern North Korea known for its hot springs and location along the Sea of Japan (East Sea).
-
D.
Dangjin
Dangjin is a coastal city in South Chungcheong Province, South Korea, known for its heavy industry, steel production, and port facilities on the Yellow Sea.
-
E.
Icheon
Icheon is a South Korean city renowned for its traditional ceramics and hot spring resorts.
- 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_69d889e0385081908a04b66f4dd4bd0d |
completed | April 10, 2026, 5:25 a.m. |
| NER | Named-entity recognition | batch_69e459324aa48190ae23fcae6e8919f8 |
completed | April 19, 2026, 4:25 a.m. |
Created at: April 10, 2026, 5:50 a.m.