Triple
T17437051
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Dodes'ka-den |
E424025
|
entity |
| Predicate | castMember |
P1668
|
FINISHED |
| Object | Yoshitaka Zushi |
—
|
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: Yoshitaka Zushi | Statement: [Dodes'ka-den, castMember, Yoshitaka Zushi]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Yoshitaka Zushi Context triple: [Dodes'ka-den, castMember, Yoshitaka Zushi]
-
A.
Yoshitaka Zushi
chosen
Yoshitaka Zushi is a Japanese actor best known for his prominent role in Akira Kurosawa’s film "Dodes'ka-den."
-
B.
Hyakutake Yuji
Hyakutake Yuji is a Japanese amateur astronomer best known for discovering Comet Hyakutake, one of the brightest and most widely observed comets of the 20th century.
-
C.
Akito Yamazaki
Akito Yamazaki is a mountaineer known for making the first recorded ascent of the Karakoram peak Ultar Sar.
-
D.
Okamura Shun
Okamura Shun is a Japanese individual notable enough to be recognized as a prominent bearer of the surname Okamura, likely in fields such as entertainment, sports, or the arts.
-
E.
Okamura Yuji
Okamura Yuji is a Japanese individual notable enough to be specifically cited as a bearer of the surname Okamura.
- 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_69d889d88b6081908bada047f5b3ba51 |
completed | April 10, 2026, 5:25 a.m. |
| NER | Named-entity recognition | batch_69e44ff468a08190bdc5cebb8162b4ba |
completed | April 19, 2026, 3:45 a.m. |
Created at: April 10, 2026, 5:46 a.m.