Triple
T21996678
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Oka-dera |
E543222
|
entity |
| Predicate | hasDeity |
P5606
|
FINISHED |
| Object | Nyoirin Kannon |
—
|
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: Nyoirin Kannon | Statement: [Oka-dera, hasDeity, Nyoirin Kannon]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Nyoirin Kannon Context triple: [Oka-dera, hasDeity, Nyoirin Kannon]
-
A.
Kannon
chosen
Kannon is the Japanese name for the bodhisattva of compassion, derived from the Buddhist deity Avalokiteshvara and widely venerated in Japan.
-
B.
Ōsu Kannon
Ōsu Kannon is a famous Buddhist temple in Nagoya, Japan, known for its large wooden statue of Kannon and its surrounding shopping arcade.
-
C.
Kannonji no misasagi
Kannonji no misasagi is an imperial mausoleum in Japan that serves as the traditional burial site of Emperor Sanjō.
-
D.
Hime no Mae
Hime no Mae was a noblewoman of the late Heian to early Kamakura period, best known as the wife of the second Kamakura shogun, Minamoto no Yoriie.
-
E.
Yoidore tenshi
Yoidore tenshi is a 1948 Japanese film directed by Akira Kurosawa, notable for its postwar noir atmosphere and early collaboration with actor Toshiro Mifune.
- 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_69e11e2c814c8190837d072789000486 |
completed | April 16, 2026, 5:36 p.m. |
| NER | Named-entity recognition | batch_69f12765fb0c81908f7b7acda065ee2f |
completed | April 28, 2026, 9:32 p.m. |
Created at: April 16, 2026, 8:19 p.m.