Triple
T17459386
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Shobijin |
E425112
|
entity |
| Predicate | portrayedBy |
P1507
|
FINISHED |
| Object | Yumi Ito |
—
|
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: Yumi Ito | Statement: [Shobijin, portrayedBy, Yumi Ito]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Yumi Ito Context triple: [Shobijin, portrayedBy, Yumi Ito]
-
A.
Yuki Ito
Yuki Ito is a prominent Japanese ski jumper known for her success in international women's ski jumping competitions, including World Cup victories and World Championship medals.
-
B.
Ayumi Ito
Ayumi Ito is a Japanese actress known for her film and television roles, including work in both domestic productions and international projects.
-
C.
Emi Ito
chosen
Emi Ito is a Japanese actress best known as one of the twin fairies, the Shobijin, in the classic Godzilla and Mothra kaiju films.
-
D.
Takako Doi
Takako Doi was a pioneering Japanese politician who became the first female Speaker of the House of Representatives and a prominent leader of Japan’s socialist and opposition politics in the late 20th century.
-
E.
Yumi Shirakawa
Yumi Shirakawa was a Japanese actress known for her prominent roles in 1950s and 1960s genre and drama films, including several classic Toho productions.
- 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_69d889db0ba481908402409af3b37917 |
completed | April 10, 2026, 5:25 a.m. |
| NER | Named-entity recognition | batch_69e451444e008190944d9668d4d901fa |
completed | April 19, 2026, 3:51 a.m. |
Created at: April 10, 2026, 5:47 a.m.