Triple
T22852752
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | East Coast of South Korea |
E566395
|
entity |
| Predicate | hasMajorCity |
P316
|
FINISHED |
| Object | Samcheok |
—
|
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: Samcheok | Statement: [East Coast of South Korea, hasMajorCity, Samcheok]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Samcheok Context triple: [East Coast of South Korea, hasMajorCity, Samcheok]
-
A.
Samcheok
chosen
Samcheok is a coastal city in eastern South Korea known for its scenic beaches, limestone caves, and maritime culture.
-
B.
Sangju
Sangju is a city in southeastern South Korea known historically for agriculture, particularly rice and dried persimmons, and for its role as a regional transport hub.
-
C.
Wonju
Wonju is a city in South Korea’s Gangwon Province known historically as a strategic military site and today as a regional commercial and transportation hub.
-
D.
Yeongcheon
Yeongcheon is a city in southeastern South Korea known for its agricultural production and historical sites within North Gyeongsang Province.
-
E.
Jeongeup
Jeongeup is a city in South Korea known for its location in North Jeolla Province and its cultural and historical heritage.
- 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_69e2458750b481908a8e4cf4609cc6cf |
completed | April 17, 2026, 2:36 p.m. |
| NER | Named-entity recognition | batch_69f17eb9a5b8819091cbb4ac42fbf778 |
completed | April 29, 2026, 3:44 a.m. |
Created at: April 17, 2026, 3:36 p.m.