Triple
T8450951
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Okja |
E199795
|
entity |
| Predicate | stars |
P1956
|
FINISHED |
| Object | Steven Yeun |
E242709
|
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: Steven Yeun | Statement: [Okja, stars, Steven Yeun]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Steven Yeun Context triple: [Okja, stars, Steven Yeun]
-
A.
Steven Yeun
chosen
Steven Yeun is a Korean-American actor best known for his roles in the TV series "The Walking Dead" and the films "Minari" and "Burning."
-
B.
Lee Jung-jae
Lee Jung-jae is a South Korean actor and former model renowned for his versatile film and television roles, gaining worldwide fame for his performance in the Netflix series "Squid Game."
-
C.
Park Du-eul
Park Du-eul is best known as the wife of Samsung founder Lee Byung-chul and a member of the influential family behind the Samsung business empire.
-
D.
Byung-hun Lee
Byung-hun Lee is a prominent South Korean actor known internationally for his roles in both Korean cinema and Hollywood films, including major action and thriller productions.
-
E.
Sung Kang
Sung Kang is an American actor best known for his role as Han Lue in the Fast & Furious film franchise.
- 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_69ca8318231881908fd1bc1c4d45d286 |
completed | March 30, 2026, 2:05 p.m. |
| NER | Named-entity recognition | batch_69cbe44815488190a912d63512e19af0 |
completed | March 31, 2026, 3:12 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ce39c11a488190b7775002e419eee7 |
completed | April 2, 2026, 9:41 a.m. |
Created at: March 30, 2026, 6:09 p.m.