Triple
T15025583
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ryōzenji |
E378203
|
entity |
| Predicate | dedicatedTo |
P500
|
FINISHED |
| Object | Shaka Nyorai |
E472639
|
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: Shaka Nyorai | Statement: [Ryōzenji, dedicatedTo, Shaka Nyorai]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Shaka Nyorai Context triple: [Ryōzenji, dedicatedTo, Shaka Nyorai]
-
A.
Shaka Nyorai
chosen
Shaka Nyorai is the Japanese name for Shakyamuni Buddha, the historical Buddha revered as the central enlightened figure in many Buddhist temples and traditions in Japan.
-
B.
Zaō Gongen
Zaō Gongen is a syncretic mountain deity in Japanese religion, revered in Shugendō as a fierce protector and manifestation of multiple Buddhist and Shintō divinities.
-
C.
Amida
Amida was the ancient name of the city now known as Diyarbakır, a historically significant fortified settlement in southeastern Anatolia.
-
D.
Yamaraja
Yamaraja is the Hindu god of death and justice, who judges the souls of the dead and presides over the afterlife.
-
E.
Nishiarai Daishi
Nishiarai Daishi is a prominent Buddhist temple in Tokyo, Japan, known as a major pilgrimage site dedicated to warding off misfortune and bringing good luck.
- 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_69d85cd46b2c819090d054c27787f677 |
completed | April 10, 2026, 2:13 a.m. |
| NER | Named-entity recognition | batch_69ded7dfcb508190aec8cd667e27a8ea |
completed | April 15, 2026, 12:12 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69fe9dd746008190a7347368ee6d20cf |
completed | May 9, 2026, 2:37 a.m. |
Created at: April 10, 2026, 2:57 a.m.