Triple
T21834077
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 伊東豊雄 |
E539073
|
entity |
| Predicate | 師事した人物 |
P38326
|
FINISHED |
| Object | 菊竹清訓 |
—
|
NE NERFINISHED |
How this triple was built (2 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: 菊竹清訓 | Statement: [伊東豊雄, 師事した人物, 菊竹清訓]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: 菊竹清訓 Context triple: [伊東豊雄, 師事した人物, 菊竹清訓]
-
A.
菊竹清訓
chosen
菊竹清訓 was a pioneering Japanese architect and leading figure of the Metabolist movement, known for visionary, modular designs that explored flexible and expandable urban structures.
-
B.
齊藤
齊藤 is a Japanese surname, typically read as "Saitō," borne by numerous individuals across Japan.
-
C.
緒方竹虎
緒方竹虎は、戦後日本の保守政治を牽引し、新聞人としても活躍した自由党系の有力政治家である。
-
D.
竹下 登
竹下 登 was a Japanese politician who served as Prime Minister of Japan from 1987 to 1989 and was a key figure in the Liberal Democratic Party.
-
E.
勝川春章
勝川春章 was an influential 18th-century Japanese ukiyo-e artist renowned for his actor portraits and for mentoring the famous printmaker Katsushika Hokusai.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69e0c475cda88190987d08f23caebdc1 |
completed | April 16, 2026, 11:13 a.m. |
| NER | Named-entity recognition | batch_69f0a7a5eeb88190b58b5b6d363cd6e3 |
completed | April 28, 2026, 12:27 p.m. |
Created at: April 16, 2026, 6:55 p.m.