Triple
T17436380
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ran |
E424010
|
entity |
| Predicate | starring |
P1507
|
FINISHED |
| Object | Yoshiko Miyazaki |
—
|
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: Yoshiko Miyazaki | Statement: [Ran, starring, Yoshiko Miyazaki]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Yoshiko Miyazaki Context triple: [Ran, starring, Yoshiko Miyazaki]
-
A.
Yoshiko Miyazaki
chosen
Yoshiko Miyazaki is a Japanese actress known for her work in film, television, and voice acting, including roles in acclaimed productions such as Akira Kurosawa’s epic "Ran."
-
B.
Yasuko Miyamoto
Yasuko Miyamoto is the wife of renowned Japanese video game designer Shigeru Miyamoto, known as the creator of iconic Nintendo franchises like Super Mario and The Legend of Zelda.
-
C.
Mie Fukuda
Mie Fukuda is best known as the wife of former Japanese Prime Minister Takeo Fukuda.
-
D.
Michiru Ōshima
Michiru Ōshima is a Japanese composer renowned for her orchestral and soundtrack work across anime, film, and video games.
-
E.
Yuka Kashino
Yuka Kashino is a Japanese singer and dancer best known as a member of the technopop girl group Perfume.
- 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_69e4490426008190b474ed76aca5d6f3 |
completed | April 19, 2026, 3:16 a.m. |
Created at: April 10, 2026, 5:46 a.m.