Triple
T21815265
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kim Il Sung’s family |
E538589
|
entity |
| Predicate | notableMember |
P10
|
FINISHED |
| Object | Kim Kyong Hui |
—
|
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: Kim Kyong Hui | Statement: [Kim Il Sung’s family, notableMember, Kim Kyong Hui]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Kim Kyong Hui Context triple: [Kim Il Sung’s family, notableMember, Kim Kyong Hui]
-
A.
Kim Kyong Hui
chosen
Kim Kyong Hui is a North Korean politician and general, the daughter of founding leader Kim Il Sung and influential aunt of current leader Kim Jong Un.
-
B.
Kwak Sin-ae
Kwak Sin-ae is a South Korean film producer best known for producing the Academy Award–winning film "Parasite."
-
C.
Kim Young Sook
Kim Young Sook is a North Korean woman best known as one of the wives of former North Korean leader Kim Jong Il.
-
D.
Kim Jung-sook
Kim Jung-sook is a South Korean classical singer and former First Lady of South Korea, known for being married to former President Moon Jae-in.
-
E.
Suh Jin-suk
Suh Jin-suk is a notable individual who prominently bears the Korean surname Suh.
- 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_69e0c473f0f8819086c9d1b4a143bd67 |
completed | April 16, 2026, 11:13 a.m. |
| NER | Named-entity recognition | batch_69f07cc99bbc8190bf074930f361af7d |
completed | April 28, 2026, 9:24 a.m. |
Created at: April 16, 2026, 6:54 p.m.