Triple
T15399361
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 竹下登 |
E368268
|
entity |
| Predicate | 所属派閥 |
P23895
|
FINISHED |
| Object |
経世会
経世会は、竹下登らを中心に自民党内で大きな影響力を持った保守本流系の有力派閥です。
|
E1154928
|
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: 経世会 | Statement: [竹下登, 所属派閥, 経世会]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: 経世会 Context triple: [竹下登, 所属派閥, 経世会]
-
A.
Nihon Mingeikan
Nihon Mingeikan is a Tokyo museum dedicated to Japanese folk crafts, showcasing everyday handmade objects central to the mingei (folk art) movement.
-
B.
Nihon Minshutō
Nihon Minshutō was a conservative political party in Japan that existed in the mid-1950s and played a key role in the formation of the modern Liberal Democratic Party.
-
C.
Sankeien Hoshōkai Foundation
The Sankeien Hoshōkai Foundation is an organization responsible for preserving, operating, and promoting the historic Sankeien Garden in Yokohama, Japan.
-
D.
Taisei Yokusankai
Taisei Yokusankai was a wartime Japanese political organization that functioned as a single-party apparatus supporting militarist and imperial policies under Prime Minister Fumimaro Konoe during World War II.
-
E.
Keidanren
Keidanren is Japan’s most influential business federation, representing major corporations and industry groups in shaping the country’s economic and industrial policy.
- 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: 経世会 Triple: [竹下登, 所属派閥, 経世会]
Generated description
経世会は、竹下登らを中心に自民党内で大きな影響力を持った保守本流系の有力派閥です。
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: 経世会 Target entity description: 経世会は、竹下登らを中心に自民党内で大きな影響力を持った保守本流系の有力派閥です。
-
A.
Nihon Mingeikan
Nihon Mingeikan is a Tokyo museum dedicated to Japanese folk crafts, showcasing everyday handmade objects central to the mingei (folk art) movement.
-
B.
Nihon Minshutō
Nihon Minshutō was a conservative political party in Japan that existed in the mid-1950s and played a key role in the formation of the modern Liberal Democratic Party.
-
C.
Sankeien Hoshōkai Foundation
The Sankeien Hoshōkai Foundation is an organization responsible for preserving, operating, and promoting the historic Sankeien Garden in Yokohama, Japan.
-
D.
Taisei Yokusankai
Taisei Yokusankai was a wartime Japanese political organization that functioned as a single-party apparatus supporting militarist and imperial policies under Prime Minister Fumimaro Konoe during World War II.
-
E.
Keidanren
Keidanren is Japan’s most influential business federation, representing major corporations and industry groups in shaping the country’s economic and industrial policy.
- 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_69d85a16c68c819099c1b547fbc87b32 |
completed | April 10, 2026, 2:01 a.m. |
| NER | Named-entity recognition | batch_69e03e8d89e08190b7cae778d89fb5e1 |
completed | April 16, 2026, 1:42 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ff13567e3481908eb6293c6af35f3a |
completed | May 9, 2026, 10:58 a.m. |
| NEDg | Description generation | batch_69ff144af00481909191a2d33874c195 |
completed | May 9, 2026, 11:02 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69ff15ae7c9c81909fd0894e48e5b5b1 |
completed | May 9, 2026, 11:08 a.m. |
Created at: April 10, 2026, 3:19 a.m.