Triple
T22004164
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sandglass |
E543404
|
entity |
| Predicate | hasCastMember |
P2308
|
FINISHED |
| Object |
Kim Mi-kyung (actress)
Kim Mi-kyung is a South Korean character actress known for her prolific supporting roles in television dramas and films.
|
E1543749
|
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 Mi-kyung (actress) | Statement: [Sandglass, hasCastMember, Kim Mi-kyung (actress)]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Kim Mi-kyung (actress) Context triple: [Sandglass, hasCastMember, Kim Mi-kyung (actress)]
-
A.
Lee Yoo-mi
Lee Yoo-mi is a South Korean actress best known internationally for her breakout role in the Netflix series "Squid Game."
-
B.
Oh Jung-mi
Oh Jung-mi is a South Korean screenwriter best known for co-writing acclaimed films such as "Burning."
-
C.
Cho Mi-yeon
Cho Mi-yeon is a South Korean singer and actress best known as the main vocalist of the K-pop girl group (G)I-DLE.
-
D.
Jung Yu-mi
Jung Yu-mi is a South Korean actress known for her versatile performances in acclaimed films and television dramas such as "Train to Busan," "The Crucible," and "Discovery of Love."
-
E.
Shim Eun-kyung
Shim Eun-kyung is a South Korean actress known for her versatile performances in film and television, particularly in comedic and dramatic roles.
- 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 Mi-kyung (actress) Triple: [Sandglass, hasCastMember, Kim Mi-kyung (actress)]
Generated description
Kim Mi-kyung is a South Korean character actress known for her prolific supporting roles in television dramas and films.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Kim Mi-kyung (actress) Target entity description: Kim Mi-kyung is a South Korean character actress known for her prolific supporting roles in television dramas and films.
-
A.
Lee Yoo-mi
Lee Yoo-mi is a South Korean actress best known internationally for her breakout role in the Netflix series "Squid Game."
-
B.
Oh Jung-mi
Oh Jung-mi is a South Korean screenwriter best known for co-writing acclaimed films such as "Burning."
-
C.
Cho Mi-yeon
Cho Mi-yeon is a South Korean singer and actress best known as the main vocalist of the K-pop girl group (G)I-DLE.
-
D.
Jung Yu-mi
Jung Yu-mi is a South Korean actress known for her versatile performances in acclaimed films and television dramas such as "Train to Busan," "The Crucible," and "Discovery of Love."
-
E.
Shim Eun-kyung
Shim Eun-kyung is a South Korean actress known for her versatile performances in film and television, particularly in comedic and dramatic roles.
- 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_69e11e2c814c8190837d072789000486 |
completed | April 16, 2026, 5:36 p.m. |
| NER | Named-entity recognition | batch_69f1276cab5c8190ac1236fde7e0394a |
completed | April 28, 2026, 9:32 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a0b2d4c441481909e4a179d1db0a30e |
completed | May 18, 2026, 3:16 p.m. |
| NEDg | Description generation | batch_6a0b3645f5a881908b322d16c7704e27 |
completed | May 18, 2026, 3:54 p.m. |
| NED2 | Entity disambiguation (via description) | batch_6a0b3769c36081909ff732275513bb2b |
completed | May 18, 2026, 3:59 p.m. |
Created at: April 16, 2026, 8:20 p.m.