Triple
T13912157
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Miyoshi Umeki |
E334524
|
entity |
| Predicate | givenName |
P17
|
FINISHED |
| Object | Miyoshi |
—
|
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: Miyoshi | Statement: [Miyoshi Umeki, givenName, Miyoshi]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Miyoshi Context triple: [Miyoshi Umeki, givenName, Miyoshi]
-
A.
Miyoshi
chosen
Miyoshi is a Japanese city known for its scenic river valleys, historical sites, and cultural exchanges with its international sister cities.
-
B.
Sunpu
Sunpu is the former name of the Japanese castle town that developed into modern Shizuoka City, historically known as a key stronghold of the Tokugawa shogunate.
-
C.
Fujinomiya
Fujinomiya is a city in Shizuoka Prefecture, Japan, known as a major gateway to Mount Fuji and for its scenic views of the iconic volcano.
-
D.
Shimada
Shimada is the surname of the fictional Japanese ninja brothers Genji and Hanzo from Blizzard Entertainment's Overwatch franchise.
-
E.
Saijo
Saijo is a city in Ehime Prefecture on Japan’s Shikoku island, known for its industrial facilities and maritime-related industries.
- 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_69d81c5eaa9c819083b1ff8689179565 |
completed | April 9, 2026, 9:38 p.m. |
| NER | Named-entity recognition | batch_69de2723461881908376b5509ee0d530 |
completed | April 14, 2026, 11:38 a.m. |
Created at: April 9, 2026, 10:16 p.m.