Triple
T22004249
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Lee Jung-gu |
E543407
|
entity |
| Predicate | affairWith |
P23617
|
FINISHED |
| Object | Eun-yi |
—
|
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: Eun-yi | Statement: [Lee Jung-gu, affairWith, Eun-yi]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Eun-yi Context triple: [Lee Jung-gu, affairWith, Eun-yi]
-
A.
Eun-yi
chosen
Eun-yi is the naive yet increasingly tormented domestic worker at the center of the South Korean thriller "The Housemaid," whose entanglement with a wealthy family leads to devastating consequences.
-
B.
Yi Yeon
Yi Yeon is the birth name of King Seonjo, the fourteenth monarch of Korea’s Joseon dynasty, who ruled during the late 16th century including the period of the Japanese invasions.
-
C.
Ji-Yoon
Ji-Yoon is a Korean given name that can be used for people of any gender, though it is more commonly given to women.
-
D.
Ju-Hee
Ju-Hee is the child of Ji-Yoon Kim, likely a member of a Korean family.
-
E.
Kun-hee
Kun-hee is the given name of Lee Kun-hee, the influential South Korean businessman who transformed Samsung into a global technology leader.
- 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_69e11e2c814c8190837d072789000486 |
completed | April 16, 2026, 5:36 p.m. |
| NER | Named-entity recognition | batch_69f1276d81e4819083a40e51249e7fd7 |
completed | April 28, 2026, 9:32 p.m. |
Created at: April 16, 2026, 8:20 p.m.