Triple
T22308074
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Koyasan |
E551437
|
entity |
| Predicate | hasStructure |
P35
|
FINISHED |
| Object | Danjo Garan |
—
|
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: Danjo Garan | Statement: [Koyasan, hasStructure, Danjo Garan]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Danjo Garan Context triple: [Koyasan, hasStructure, Danjo Garan]
-
A.
Danjo Garan
chosen
Danjo Garan is a central sacred temple complex on Mount Koya in Japan, founded by the monk Kūkai and serving as one of the core sites of Shingon Buddhism.
-
B.
Gararu
Gararu is a municipality in the Brazilian state of Sergipe, located in the semi-arid interior region known for its rural economy and proximity to the São Francisco River.
-
C.
Gashin
Gashin are household deities in Korean mythology that protect various aspects of the home and family life.
-
D.
Jashugan
Jashugan is a legendary and fearsome Motorball champion in the manga series "Gunnm" (also known as "Battle Angel Alita"), renowned for his unmatched combat prowess and imposing presence.
-
E.
Gan-Ga
"Gan-Ga" is a popular Latin trap song by Puerto Rican artist Bryant Myers that helped solidify his presence in the urban music scene.
- 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_69e11e46c0188190800181a4233f28fe |
completed | April 16, 2026, 5:37 p.m. |
| NER | Named-entity recognition | batch_69f1574c8a248190bf5eef5be78381fd |
completed | April 29, 2026, 12:56 a.m. |
Created at: April 16, 2026, 8:41 p.m.