Triple
T23218577
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Park Bin-na |
E580818
|
entity |
| Predicate | notableStudent |
P4838
|
FINISHED |
| Object | Yuna Kim |
—
|
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: Yuna Kim | Statement: [Park Bin-na, notableStudent, Yuna Kim]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Yuna Kim Context triple: [Park Bin-na, notableStudent, Yuna Kim]
-
A.
Yuna Kim
chosen
Yuna Kim is a South Korean figure skating legend and Olympic champion widely celebrated for her technical excellence, artistry, and global impact on the sport.
-
B.
Alice Kim
Alice Kim is an American former waitress and actress best known as the ex-wife of actor Nicolas Cage.
-
C.
Nellie Kim
Nellie Kim is a former Soviet artistic gymnast renowned for her multiple Olympic gold medals in the 1970s and for pioneering difficult tumbling and vaulting skills.
-
D.
Saemi Kim
Saemi Kim is a film and television producer known for her work behind the scenes bringing scripted projects to fruition.
-
E.
Jacqueline Kim
Jacqueline Kim is an American actress and filmmaker known for her roles in films such as "Volcano," "Star Trek: Generations," and "Charlotte Sometimes."
- 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_69e2460389408190be74f41d217799a9 |
completed | April 17, 2026, 2:38 p.m. |
| NER | Named-entity recognition | batch_69f191675de48190858907872a065c56 |
completed | April 29, 2026, 5:04 a.m. |
Created at: April 17, 2026, 4:08 p.m.