Triple
T15711192
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Song Kang-ho |
E380840
|
entity |
| Predicate | nativeName |
P15
|
FINISHED |
| Object |
송강호
송강호는 다양한 영화에서 깊이 있는 연기와 폭넓은 캐릭터 소화로 국내외에서 높은 평가를 받는 대한민국의 대표적인 영화 배우이다.
|
E1173732
|
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: 송강호 | Statement: [Song Kang-ho, nativeName, 송강호]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: 송강호 Context triple: [Song Kang-ho, nativeName, 송강호]
-
A.
Song Seung-whan
Song Seung-whan is a South Korean producer, director, and actor best known internationally for directing the opening and closing ceremonies of the 2018 PyeongChang Winter Olympics.
-
B.
Hwang Jun-ho
Hwang Jun-ho is a determined police officer in the South Korean series "Squid Game" who infiltrates the deadly competition to uncover the truth behind its operations and find his missing brother.
-
C.
Han Jin-won
Han Jin-won is a South Korean screenwriter best known for co-writing the Academy Award–winning film "Parasite."
-
D.
Choi Doo-ho
Choi Doo-ho is a South Korean film producer known for his work on the critically acclaimed fantasy-adventure film "Okja."
-
E.
Kim Hong-up
Kim Hong-up is a South Korean politician and lawyer best known as the son of former President and Nobel Peace Prize laureate Kim Dae-jung.
- 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: 송강호 Triple: [Song Kang-ho, nativeName, 송강호]
Generated description
송강호는 다양한 영화에서 깊이 있는 연기와 폭넓은 캐릭터 소화로 국내외에서 높은 평가를 받는 대한민국의 대표적인 영화 배우이다.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: 송강호 Target entity description: 송강호는 다양한 영화에서 깊이 있는 연기와 폭넓은 캐릭터 소화로 국내외에서 높은 평가를 받는 대한민국의 대표적인 영화 배우이다.
-
A.
Song Seung-whan
Song Seung-whan is a South Korean producer, director, and actor best known internationally for directing the opening and closing ceremonies of the 2018 PyeongChang Winter Olympics.
-
B.
Hwang Jun-ho
Hwang Jun-ho is a determined police officer in the South Korean series "Squid Game" who infiltrates the deadly competition to uncover the truth behind its operations and find his missing brother.
-
C.
Han Jin-won
Han Jin-won is a South Korean screenwriter best known for co-writing the Academy Award–winning film "Parasite."
-
D.
Choi Doo-ho
Choi Doo-ho is a South Korean film producer known for his work on the critically acclaimed fantasy-adventure film "Okja."
-
E.
Kim Hong-up
Kim Hong-up is a South Korean politician and lawyer best known as the son of former President and Nobel Peace Prize laureate Kim Dae-jung.
- 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_69d86d9bf930819082b30cf6d169297c |
completed | April 10, 2026, 3:25 a.m. |
| NER | Named-entity recognition | batch_69e04f8f5d6081908243fa59b46b7c76 |
completed | April 16, 2026, 2:55 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ff82f22fc88190820ecb171041136d |
completed | May 9, 2026, 6:54 p.m. |
| NEDg | Description generation | batch_69ff83ff8c7481909fbc502143c1852f |
completed | May 9, 2026, 6:59 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69ff8469354c819080b8cfddb7c66be5 |
completed | May 9, 2026, 7 p.m. |
Created at: April 10, 2026, 4:45 a.m.