Triple
T13459745
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kakeromajima |
E311327
|
entity |
| Predicate | locatedSouthOf |
P9676
|
FINISHED |
| Object | Amami Ōshima |
E192624
|
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: Amami Ōshima | Statement: [Kakeromajima, locatedSouthOf, Amami Ōshima]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Amami Ōshima Context triple: [Kakeromajima, locatedSouthOf, Amami Ōshima]
-
A.
Amami Ōshima
chosen
Amami Ōshima is a subtropical Japanese island in Kagoshima Prefecture known for its rich biodiversity, coral reefs, and traditional Ryukyuan-influenced culture.
-
B.
Shijo Ohashi
Shijo Ohashi is a major bridge in central Kyoto, Japan, serving as a key crossing and landmark near the bustling Shijo district.
-
C.
Chikako Shimazu
Chikako Shimazu was a Japanese noblewoman of the influential Shimazu family and the mother of Empress Kōjun, consort of Emperor Shōwa (Hirohito).
-
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.
Okamura Akemi
Okamura Akemi is a Japanese voice actress and singer best known for voicing Nami in the long-running anime series "One Piece."
- 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_69d806a938b8819097ec43a2229fc7f9 |
completed | April 9, 2026, 8:06 p.m. |
| NER | Named-entity recognition | batch_69dbaf0c177081909178dec61b09c278 |
completed | April 12, 2026, 2:41 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f7a83382e88190bfb229f9bab59b17 |
completed | May 3, 2026, 7:55 p.m. |
Created at: April 9, 2026, 9:41 p.m.