Triple
T21869481
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Train to Busan |
E539964
|
entity |
| Predicate | portrayedBy |
P1507
|
FINISHED |
| Object |
Ahn So-hee
Ahn So-hee is a South Korean actress and former member of the K-pop girl group Wonder Girls who has appeared in various films and television dramas.
|
E1536721
|
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: Ahn So-hee | Statement: [Train to Busan, portrayedBy, Ahn So-hee]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Ahn So-hee Context triple: [Train to Busan, portrayedBy, Ahn So-hee]
-
A.
Won Jin-ah
Won Jin-ah is a South Korean actress known for her roles in television dramas and films, including the dark fantasy series "Hellbound."
-
B.
Yoon Ga-eun
Yoon Ga-eun is a South Korean film director and screenwriter known for her sensitive, realistic portrayals of children and adolescence.
-
C.
Lee Maeng-hee
Lee Maeng-hee was a South Korean businessman best known as the eldest son of Samsung founder Lee Byung-chul and a former executive within the Samsung Group.
-
D.
Yu Jae-sun
Yu Jae-sun is a film producer best known for producing the South Korean movie "Silenced."
-
E.
Kim Hye-ja
Kim Hye-ja is a renowned South Korean actress, especially acclaimed for her powerful performance in Bong Joon-ho’s thriller "Mother" and her long career in television dramas.
- 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: Ahn So-hee Triple: [Train to Busan, portrayedBy, Ahn So-hee]
Generated description
Ahn So-hee is a South Korean actress and former member of the K-pop girl group Wonder Girls who has appeared in various films and television dramas.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Ahn So-hee Target entity description: Ahn So-hee is a South Korean actress and former member of the K-pop girl group Wonder Girls who has appeared in various films and television dramas.
-
A.
Won Jin-ah
Won Jin-ah is a South Korean actress known for her roles in television dramas and films, including the dark fantasy series "Hellbound."
-
B.
Yoon Ga-eun
Yoon Ga-eun is a South Korean film director and screenwriter known for her sensitive, realistic portrayals of children and adolescence.
-
C.
Lee Maeng-hee
Lee Maeng-hee was a South Korean businessman best known as the eldest son of Samsung founder Lee Byung-chul and a former executive within the Samsung Group.
-
D.
Yu Jae-sun
Yu Jae-sun is a film producer best known for producing the South Korean movie "Silenced."
-
E.
Kim Hye-ja
Kim Hye-ja is a renowned South Korean actress, especially acclaimed for her powerful performance in Bong Joon-ho’s thriller "Mother" and her long career in television dramas.
- 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_6a0b0c554fac81908e6159bba70e310e |
completed | May 18, 2026, 12:55 p.m. |
| NEDg | Description generation | batch_6a0b0cfa58cc819085e976bf76fbf149 |
completed | May 18, 2026, 12:58 p.m. |
| NED2 | Entity disambiguation (via description) | batch_6a0b0d534f1481908e74f754426d321f |
completed | May 18, 2026, 1 p.m. |
Created at: April 16, 2026, 6:57 p.m.