Triple
T10969374
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Koh |
E259190
|
entity |
| Predicate | hasNotableBearer |
P458
|
FINISHED |
| Object |
Koh Bong-joon
Koh Bong-joon is a Korean individual notable enough to be recognized as a prominent bearer of the surname Koh.
|
E897458
|
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: Koh Bong-joon | Statement: [Koh, hasNotableBearer, Koh Bong-joon]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Koh Bong-joon Context triple: [Koh, hasNotableBearer, Koh Bong-joon]
-
A.
Dong Maeng
Dong Maeng is a joint South Korea–United States military exercise that succeeded earlier large-scale drills as part of their combined defense posture.
-
B.
Yong Duk Jhun
Yong Duk Jhun is a South Korean-born cinematographer and animator best known for his visual work on major DreamWorks animated films, including the Kung Fu Panda series.
-
C.
Gim Man-il
Gim Man-il is the revised Romanization form of the Korean personal name more commonly known in older systems as Kim Man-il.
-
D.
Yong-il
Yong-il is a Korean masculine given name that can be shared by various individuals, including notable figures such as politicians and public officials.
-
E.
Seonghwan
Seonghwan is a locality in South Korea historically noted as the site of the Battle of Seonghwan during the First Sino-Japanese War.
- 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: Koh Bong-joon Triple: [Koh, hasNotableBearer, Koh Bong-joon]
Generated description
Koh Bong-joon is a Korean individual notable enough to be recognized as a prominent bearer of the surname Koh.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Koh Bong-joon Target entity description: Koh Bong-joon is a Korean individual notable enough to be recognized as a prominent bearer of the surname Koh.
-
A.
Dong Maeng
Dong Maeng is a joint South Korea–United States military exercise that succeeded earlier large-scale drills as part of their combined defense posture.
-
B.
Yong Duk Jhun
Yong Duk Jhun is a South Korean-born cinematographer and animator best known for his visual work on major DreamWorks animated films, including the Kung Fu Panda series.
-
C.
Gim Man-il
Gim Man-il is the revised Romanization form of the Korean personal name more commonly known in older systems as Kim Man-il.
-
D.
Yong-il
Yong-il is a Korean masculine given name that can be shared by various individuals, including notable figures such as politicians and public officials.
-
E.
Seonghwan
Seonghwan is a locality in South Korea historically noted as the site of the Battle of Seonghwan during the First Sino-Japanese War.
- 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_69d6aa895f4c8190887a15460ef622f4 |
completed | April 8, 2026, 7:20 p.m. |
| NER | Named-entity recognition | batch_69d77198e5408190904b2bb603d1bc16 |
completed | April 9, 2026, 9:30 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69e2d790df108190b4a3a6fece372778 |
completed | April 18, 2026, 1 a.m. |
| NEDg | Description generation | batch_69e2ff1ffb8c8190ba97f3c2e3c8c601 |
completed | April 18, 2026, 3:48 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69e3261cc4f48190ba0e5645f37cd4b5 |
completed | April 18, 2026, 6:35 a.m. |
Created at: April 8, 2026, 9:24 p.m.