Triple
T22004108
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sandglass |
E543404
|
entity |
| Predicate | hasCastMember |
P2308
|
FINISHED |
| Object | Kim Hye-sun |
—
|
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 Hye-sun | Statement: [Sandglass, hasCastMember, Kim Hye-sun]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Kim Hye-sun Context triple: [Sandglass, hasCastMember, Kim Hye-sun]
-
A.
Koo Hye-sun
Koo Hye-sun is a South Korean actress, director, singer-songwriter, and artist best known for her leading role in the hit drama "Boys Over Flowers" and her multifaceted work in film and music.
-
B.
Hong Yoon-jeong
Hong Yoon-jeong is a South Korean screenwriter best known for her work on the hit fantasy-comedy film "Miss Granny."
-
C.
Kim Soo-mi
Kim Soo-mi is a veteran South Korean actress renowned for her prolific film and television career, particularly in comedy and family dramas.
-
D.
Seol Hye-in
Seol Hye-in is a South Korean actress known for her role in the coming-of-age film "The World of Us."
-
E.
Jeon Hye-jin
Jeon Hye-jin is a South Korean actress known for her work in film and television.
- F. None of above. chosen
- 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_69e11e2c814c8190837d072789000486 |
completed | April 16, 2026, 5:36 p.m. |
| NER | Named-entity recognition | batch_69f1276cab5c8190ac1236fde7e0394a |
completed | April 28, 2026, 9:32 p.m. |
Created at: April 16, 2026, 8:20 p.m.