Triple
T13174284
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Koyama Mihoko |
E313059
|
entity |
| Predicate | name |
P16
|
FINISHED |
| Object | Koyama Mihoko |
E313059
|
NE FINISHED |
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: Koyama Mihoko | Statement: [Koyama Mihoko, name, Koyama Mihoko]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Koyama Mihoko Context triple: [Koyama Mihoko, name, Koyama Mihoko]
-
A.
Koyama Mihoko
chosen
Koyama Mihoko is a Japanese philanthropist and art collector best known as the founder and patron of the Miho Museum in Shiga Prefecture, Japan.
-
B.
Okamura Mayumi
Okamura Mayumi is a Japanese voice actress and singer known for her work in anime and related media.
-
C.
Kaho Shimada
Kaho Shimada is a Japanese actress and singer best known internationally for her acclaimed stage performances in musical theatre, particularly in productions of Les Misérables.
-
D.
Tanaka Makiko
Tanaka Makiko is a Japanese politician and former foreign minister known for her reformist stance and outspoken criticism of Japan’s political establishment.
-
E.
Ayumi Sekine
Ayumi Sekine is a Japanese screenwriter best known for her work on anime projects, including the Fate/Grand Order - First Order adaptation.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (3 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_69d806ac3ee081909b2fd27d060aa974 |
completed | April 9, 2026, 8:06 p.m. |
| NER | Named-entity recognition | batch_69d98c303e3c819086cf0f0b6d9e61ca |
completed | April 10, 2026, 11:48 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f73970791c8190af0facf83b0a2107 |
completed | May 3, 2026, 12:02 p.m. |
Created at: April 9, 2026, 9:14 p.m.