Triple
T15711198
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Song Kang-ho |
E380840
|
entity |
| Predicate | spouse |
P13
|
FINISHED |
| Object |
Hwang Jang-suk
Hwang Jang-suk is the wife of acclaimed South Korean actor Song Kang-ho.
|
E1178263
|
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: Hwang Jang-suk | Statement: [Song Kang-ho, spouse, Hwang Jang-suk]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Hwang Jang-suk Context triple: [Song Kang-ho, spouse, Hwang Jang-suk]
-
A.
Chung Ju-yung
Chung Ju-yung was a South Korean entrepreneur and industrialist who built the Hyundai conglomerate into one of the country’s largest and most influential business empires.
-
B.
Jang Kum-song
Jang Kum-song was the daughter of senior North Korean official Kim Kyong-hui and thus a member of North Korea’s ruling Kim family.
-
C.
Won In-choul
Won In-choul is a South Korean Air Force general who served as the country’s Chairman of the Joint Chiefs of Staff.
-
D.
Ahn Eak-tai
Ahn Eak-tai was a Korean composer and conductor best known for writing the music that became South Korea’s national anthem.
-
E.
Chang Sŏng-t’aek
Chang Sŏng-t’aek was a powerful North Korean politician and uncle by marriage to Kim Jong-un who was once considered the country’s second-most influential figure before his dramatic purge and execution in 2013.
- 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: Hwang Jang-suk Triple: [Song Kang-ho, spouse, Hwang Jang-suk]
Generated description
Hwang Jang-suk is the wife of acclaimed South Korean actor Song Kang-ho.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Hwang Jang-suk Target entity description: Hwang Jang-suk is the wife of acclaimed South Korean actor Song Kang-ho.
-
A.
Chung Ju-yung
Chung Ju-yung was a South Korean entrepreneur and industrialist who built the Hyundai conglomerate into one of the country’s largest and most influential business empires.
-
B.
Jang Kum-song
Jang Kum-song was the daughter of senior North Korean official Kim Kyong-hui and thus a member of North Korea’s ruling Kim family.
-
C.
Won In-choul
Won In-choul is a South Korean Air Force general who served as the country’s Chairman of the Joint Chiefs of Staff.
-
D.
Ahn Eak-tai
Ahn Eak-tai was a Korean composer and conductor best known for writing the music that became South Korea’s national anthem.
-
E.
Chang Sŏng-t’aek
Chang Sŏng-t’aek was a powerful North Korean politician and uncle by marriage to Kim Jong-un who was once considered the country’s second-most influential figure before his dramatic purge and execution in 2013.
- 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_69ff997fe6f48190813bde2bfc11c253 |
completed | May 9, 2026, 8:30 p.m. |
| NEDg | Description generation | batch_69ff9a0fdf388190b2742e19f307c570 |
completed | May 9, 2026, 8:33 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69ff9a77d6d88190817158c30c56d70c |
completed | May 9, 2026, 8:35 p.m. |
Created at: April 10, 2026, 4:45 a.m.