Triple
T7995311
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Youn Yuh-jung |
E186109
|
entity |
| Predicate | givenName |
P17
|
FINISHED |
| Object | Yuh-jung |
E186109
|
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: Yuh-jung | Statement: [Youn Yuh-jung, givenName, Yuh-jung]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Yuh-jung Context triple: [Youn Yuh-jung, givenName, Yuh-jung]
-
A.
Youn Yuh-jung
chosen
Youn Yuh-jung is a renowned South Korean actress acclaimed for her decades-long career in film and television and for becoming one of the first Korean performers to gain major recognition in Western awards circles.
-
B.
Ban Hyun-hee
Ban Hyun-hee is a child of Yoo Soon-taek, who is known as the spouse of former UN Secretary-General Ban Ki-moon.
-
C.
Shin Hye-sook
Shin Hye-sook is a South Korean figure skating coach best known for working with Olympic champion Yuna Kim during her early development.
-
D.
Hae-in Jung
Hae-in Jung is a South Korean actor known for his roles in television dramas and films.
-
E.
Kim Sung-ae
Kim Sung-ae was the second wife of North Korean leader Kim Il Sung and a prominent political figure who headed the country’s women’s organization.
- 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_69ca829c6c308190ab05b43d234c52b2 |
completed | March 30, 2026, 2:03 p.m. |
| NER | Named-entity recognition | batch_69cb3c7547dc8190a60a06b3d61764b0 |
completed | March 31, 2026, 3:16 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69cc63bcae048190a3fd151b2d8f9f77 |
completed | April 1, 2026, 12:15 a.m. |
Created at: March 30, 2026, 5:17 p.m.