Triple
T21869422
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | The Handmaiden |
E539963
|
entity |
| Predicate | starring |
P1507
|
FINISHED |
| Object |
Kim Min-hee
Kim Min-hee is a South Korean actress acclaimed for her nuanced performances in both mainstream and arthouse cinema, particularly in collaboration with director Hong Sang-soo.
|
E1532617
|
NE FINISHED |
How this triple was built (4 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 Min-hee | Statement: [The Handmaiden, starring, Kim Min-hee]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Kim Min-hee Context triple: [The Handmaiden, starring, Kim Min-hee]
-
A.
Kim Tae-hee
Kim Tae-hee is a South Korean actress renowned for her roles in popular television dramas such as "Stairway to Heaven," "Love Story in Harvard," and "Iris."
-
B.
Lee In-hee
Lee In-hee is a South Korean businesswoman and heiress known as a prominent member of the Samsung founding family.
-
C.
Park Ye-rin
Park Ye-rin is a South Korean actress known for her role in the sci-fi film "Space Sweepers."
-
D.
Han Ye-ri
Han Ye-ri is a South Korean actress known for her nuanced performances in film and television, including her acclaimed role in the drama "Minari."
-
E.
Hong Yoon-jeong
Hong Yoon-jeong is a South Korean screenwriter best known for her work on the hit fantasy-comedy film "Miss Granny."
- F. None of above. chosen
- G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg
Description generation
gpt-5.1
Instruction
Generate a one-sentence description of the target entity. You are given a context triple in the form (subject, predicate, object), where the object is the target entity. # Instructions Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. Avoid repeating the information from the triple, unless really essential. # Response Format Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Kim Min-hee Triple: [The Handmaiden, starring, Kim Min-hee]
Generated description
Kim Min-hee is a South Korean actress acclaimed for her nuanced performances in both mainstream and arthouse cinema, particularly in collaboration with director Hong Sang-soo.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Kim Min-hee Target entity description: Kim Min-hee is a South Korean actress acclaimed for her nuanced performances in both mainstream and arthouse cinema, particularly in collaboration with director Hong Sang-soo.
-
A.
Kim Tae-hee
Kim Tae-hee is a South Korean actress renowned for her roles in popular television dramas such as "Stairway to Heaven," "Love Story in Harvard," and "Iris."
-
B.
Lee In-hee
Lee In-hee is a South Korean businesswoman and heiress known as a prominent member of the Samsung founding family.
-
C.
Park Ye-rin
Park Ye-rin is a South Korean actress known for her role in the sci-fi film "Space Sweepers."
-
D.
Han Ye-ri
Han Ye-ri is a South Korean actress known for her nuanced performances in film and television, including her acclaimed role in the drama "Minari."
-
E.
Hong Yoon-jeong
Hong Yoon-jeong is a South Korean screenwriter best known for her work on the hit fantasy-comedy film "Miss Granny."
- F. None of above. chosen
Provenance (5 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_69e0c478f59081909d54302b57fc1ce3 |
completed | April 16, 2026, 11:14 a.m. |
| NER | Named-entity recognition | batch_69f0f334362c819094af465ee57b47e6 |
completed | April 28, 2026, 5:49 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a0ae04516308190b89d9ecf960e6acf |
completed | May 18, 2026, 9:47 a.m. |
| NEDg | Description generation | batch_6a0ae2cff2188190a4e3bcbd2bb559a3 |
completed | May 18, 2026, 9:58 a.m. |
| NED2 | Entity disambiguation (via description) | batch_6a0ae36819548190a475410927ea89f3 |
completed | May 18, 2026, 10:01 a.m. |
Created at: April 16, 2026, 6:57 p.m.