Triple
T17242558
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kim Chaek City |
E418537
|
entity |
| Predicate | namedAfter |
P63
|
FINISHED |
| Object | Kim Chaek |
E85039
|
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: Kim Chaek | Statement: [Kim Chaek City, namedAfter, Kim Chaek]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Kim Chaek Context triple: [Kim Chaek City, namedAfter, Kim Chaek]
-
A.
Kim Chaek
chosen
Kim Chaek was a prominent North Korean military commander and close ally of Kim Il-sung who played a key leadership role in the early stages of the Korean War.
-
B.
Ko Un
Ko Un is a prominent South Korean poet, former Buddhist monk, and activist renowned for his prolific output and his role as a leading figure in contemporary Korean literature.
-
C.
Kim Man-il
Kim Man-il was the younger son of North Korean leader Kim Il Sung, who died in childhood and is remembered primarily within the context of the ruling Kim family’s history.
-
D.
Kim Tok Hun
Kim Tok Hun is a North Korean politician who serves as the country’s premier, effectively acting as its head of government.
-
E.
Kim Yong-il
Kim Yong-il is a North Korean politician and technocrat who served as the country's Premier from 2007 to 2010.
- 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_69d886d8e96081909870bff6c3d0bf09 |
completed | April 10, 2026, 5:12 a.m. |
| NER | Named-entity recognition | batch_69e42e21003c81908c884a3c8712676a |
completed | April 19, 2026, 1:21 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a0170f388608190b709b1c228a7ba29 |
completed | May 11, 2026, 6:02 a.m. |
Created at: April 10, 2026, 5:39 a.m.