Triple
T23407521
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Hwang Kyo-ahn |
E559974
|
entity |
| Predicate | successorAsPresident |
P10458
|
FINISHED |
| Object | Moon Jae-in |
—
|
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: Moon Jae-in | Statement: [Hwang Kyo-ahn, successorAsPresident, Moon Jae-in]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Moon Jae-in Context triple: [Hwang Kyo-ahn, successorAsPresident, Moon Jae-in]
-
A.
Moon Jae-in
chosen
Moon Jae-in is a South Korean politician and former human rights lawyer who served as the President of South Korea from 2017 to 2022.
-
B.
Yoon Suk-yeol
Yoon Suk-yeol is the President of South Korea, a former prosecutor known for his tough stance on corruption and conservative political views.
-
C.
Kim Chunchu
Kim Chunchu, better known by his temple name King Taejong Muyeol, was a 7th-century monarch of the Korean kingdom of Silla who played a key role in the unification of the Korean Peninsula.
-
D.
박근혜
박근혜는 대한민국의 제18대 대통령으로, 한국 최초의 여성 대통령이자 박정희 전 대통령의 딸이다.
-
E.
John Kim
John Kim is an Australian actor best known for his role as Ezekiel Jones in the fantasy-adventure television series "The Librarians."
- 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_69e2454b3a5881909c64773dc8a5d289 |
completed | April 17, 2026, 2:35 p.m. |
| NER | Named-entity recognition | batch_69f1a50f3f90819084fb682597fee1e1 |
completed | April 29, 2026, 6:28 a.m. |
Created at: April 17, 2026, 5:38 p.m.