Triple
T13826013
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tanabe |
E332249
|
entity |
| Predicate | isGatewayTo |
P2066
|
FINISHED |
| Object | Kumano Sanzan |
E133735
|
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: Kumano Sanzan | Statement: [Tanabe, isGatewayTo, Kumano Sanzan]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Kumano Sanzan Context triple: [Tanabe, isGatewayTo, Kumano Sanzan]
-
A.
Kumano Sanzan
chosen
Kumano Sanzan is a sacred trio of ancient Shinto-Buddhist shrines in Japan’s Kii Mountains, renowned as a major pilgrimage center and part of the UNESCO-listed Kumano Kodo routes.
-
B.
Kumano Gongen
Kumano Gongen is a syncretic Shinto-Buddhist manifestation of deities venerated at the Kumano shrines, revered as protective and salvific mountain and pilgrimage gods in Japan.
-
C.
Kumano Shrine
Kumano Shrine is a traditional Shinto shrine located in Tokyo’s Jiyūgaoka district, known for its serene atmosphere amid the surrounding urban shopping area.
-
D.
Kumano
Kumano was a Mogami-class heavy cruiser of the Imperial Japanese Navy that served during World War II.
-
E.
Kumano
Kumano is a coastal city in Japan’s Mie Prefecture known for its scenic Kumano Kodo pilgrimage routes and rugged natural landscapes.
- 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_69d81c5ae7c88190b0dd41bdafeb5999 |
completed | April 9, 2026, 9:38 p.m. |
| NER | Named-entity recognition | batch_69de0295d2d48190b08eba0d805bd72d |
completed | April 14, 2026, 9:02 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f7b8e85c6c81908bdf5d43b917d151 |
completed | May 3, 2026, 9:06 p.m. |
Created at: April 9, 2026, 10:13 p.m.