Triple
T8624595
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Imamura Shohei |
E204251
|
entity |
| Predicate | spouse |
P13
|
FINISHED |
| Object |
Imamura Kazuko
Imamura Kazuko is best known as the wife of acclaimed Japanese film director Shohei Imamura.
|
E772254
|
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: Imamura Kazuko | Statement: [Imamura Shohei, spouse, Imamura Kazuko]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Imamura Kazuko Context triple: [Imamura Shohei, spouse, Imamura Kazuko]
-
A.
Yoshida Yukiko
Yoshida Yukiko was the wife of Shigeru Yoshida, a prominent post–World War II Japanese prime minister and key architect of Japan’s modern foreign policy.
-
B.
Machiko Yamada
Machiko Yamada is a prominent Japanese figure skating coach known for mentoring world champion skater Midori Ito and developing numerous elite athletes.
-
C.
Shōda Fumiko
Shōda Fumiko was a Japanese noblewoman and matriarch of the Shōda family, best known as the mother of Empress Michiko of Japan.
-
D.
Kawashima Kiko
Kawashima Kiko, better known as Princess Kiko, is a member of the Japanese imperial family and the wife of Crown Prince Fumihito (Prince Akishino).
-
E.
Tanaka Kinuyo
Tanaka Kinuyo was a pioneering Japanese actress and one of Japan’s first prominent female film directors, renowned for her work in classic mid-20th-century cinema.
- 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: Imamura Kazuko Triple: [Imamura Shohei, spouse, Imamura Kazuko]
Generated description
Imamura Kazuko is best known as the wife of acclaimed Japanese film director Shohei Imamura.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Imamura Kazuko Target entity description: Imamura Kazuko is best known as the wife of acclaimed Japanese film director Shohei Imamura.
-
A.
Yoshida Yukiko
Yoshida Yukiko was the wife of Shigeru Yoshida, a prominent post–World War II Japanese prime minister and key architect of Japan’s modern foreign policy.
-
B.
Machiko Yamada
Machiko Yamada is a prominent Japanese figure skating coach known for mentoring world champion skater Midori Ito and developing numerous elite athletes.
-
C.
Shōda Fumiko
Shōda Fumiko was a Japanese noblewoman and matriarch of the Shōda family, best known as the mother of Empress Michiko of Japan.
-
D.
Kawashima Kiko
Kawashima Kiko, better known as Princess Kiko, is a member of the Japanese imperial family and the wife of Crown Prince Fumihito (Prince Akishino).
-
E.
Tanaka Kinuyo
Tanaka Kinuyo was a pioneering Japanese actress and one of Japan’s first prominent female film directors, renowned for her work in classic mid-20th-century cinema.
- 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_69ca834a4ea0819094970dceb9e389f3 |
completed | March 30, 2026, 2:06 p.m. |
| NER | Named-entity recognition | batch_69cc4728360c8190b5e600596cbced0c |
completed | March 31, 2026, 10:14 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69cfdb759f6c819085939e38e0281361 |
completed | April 3, 2026, 3:23 p.m. |
| NEDg | Description generation | batch_69cfdbeba3808190b3d11a45bce24c80 |
completed | April 3, 2026, 3:25 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69cfdc391e6081909b1f3ff823ce174d |
completed | April 3, 2026, 3:26 p.m. |
Created at: March 30, 2026, 6:26 p.m.