Triple
T8450933
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Okja |
E199795
|
entity |
| Predicate | editedBy |
P1954
|
FINISHED |
| Object | Yang Jin-mo |
E404465
|
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: Yang Jin-mo | Statement: [Okja, editedBy, Yang Jin-mo]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Yang Jin-mo Context triple: [Okja, editedBy, Yang Jin-mo]
-
A.
Yang Jin-mo
chosen
Yang Jin-mo is a South Korean film editor best known for his acclaimed work on the Academy Award–winning film "Parasite."
-
B.
Jung Sun-young
Jung Sun-young is the wife of acclaimed South Korean film director Bong Joon-ho.
-
C.
Jin Ha
Jin Ha is a Korean-American actor known for his roles in television series such as "Devs" and "Pachinko," as well as his work on stage in productions like "Hamilton."
-
D.
Jung Ho-yeon
Jung Ho-yeon is a South Korean model-turned-actress who gained international fame for her breakout role in the Netflix survival drama series "Squid Game."
-
E.
Ko Woo-rim
Ko Woo-rim is a South Korean classical crossover singer best known as a member of the vocal quartet Forestella and for being married to figure skating champion Yuna Kim.
- 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_69ce6cf9368081909cad61cdf6156a0e |
completed | April 2, 2026, 1:19 p.m. |
Created at: March 30, 2026, 6:09 p.m.