Triple
T18028955
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kiki Sukezane |
E431335
|
entity |
| Predicate | name |
P16
|
FINISHED |
| Object | Kiki Sukezane |
—
|
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: Kiki Sukezane | Statement: [Kiki Sukezane, name, Kiki Sukezane]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Kiki Sukezane Context triple: [Kiki Sukezane, name, Kiki Sukezane]
-
A.
Kiki Sukezane
chosen
Kiki Sukezane is a Japanese actress best known internationally for her roles in genre television series such as "Heroes Reborn" and the horror anthology "The Terror."
-
B.
Kaori Icho
Kaori Icho is a legendary Japanese freestyle wrestler, renowned as a four-time consecutive Olympic gold medalist and one of the most dominant athletes in the sport’s history.
-
C.
Rei Kikukawa
Rei Kikukawa is a Japanese actress and television presenter known for her roles in film and TV, including a prominent appearance in the Godzilla franchise.
-
D.
Mitsuki Koga
Mitsuki Koga is a Japanese actor and martial artist known for his roles in action and tokusatsu films, including entries in the Godzilla franchise.
-
E.
Takako Kawai
Takako Kawai is a Japanese mathematician known for her work in algebraic analysis and microlocal analysis.
- 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_69d8b9050fb48190890155145deb0a66 |
completed | April 10, 2026, 8:47 a.m. |
| NER | Named-entity recognition | batch_69e4be332a7081909124abdd98430a8a |
completed | April 19, 2026, 11:36 a.m. |
Created at: April 10, 2026, 10:25 a.m.