Triple
T14964580
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Temple 27: Kōnomineji |
E373155
|
entity |
| Predicate | hasAlias |
P455
|
FINISHED |
| Object | Kōnomine-ji |
—
|
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: Kōnomine-ji | Statement: [Temple 27: Kōnomineji, hasAlias, Kōnomine-ji]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Kōnomine-ji Context triple: [Temple 27: Kōnomineji, hasAlias, Kōnomine-ji]
-
A.
Konomine-ji
chosen
Konomine-ji is a Buddhist temple in Kōchi Prefecture, Japan, known as Temple 27 on the Shikoku Pilgrimage.
-
B.
Shiromine-ji
Shiromine-ji is a Buddhist temple in Kagawa Prefecture, Japan, known as Temple 81 on the Shikoku Pilgrimage.
-
C.
Kenchō-ji
Kenchō-ji is a historic Zen Buddhist temple in Kamakura, Japan, renowned as one of the oldest and most important Zen training monasteries in the country.
-
D.
Juraku-ji
Juraku-ji is a Buddhist temple in Japan known as Temple 7 on the Shikoku Pilgrimage route.
-
E.
Kodai-ji
Kodai-ji is a historic Zen Buddhist temple in Kyoto renowned for its beautiful gardens, traditional architecture, and connections to the warlord Toyotomi Hideyoshi.
- 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_69d85ccbbcd48190acb56e7cf104d8ad |
completed | April 10, 2026, 2:13 a.m. |
| NER | Named-entity recognition | batch_69ded6d0487c8190b7754af8c5014b37 |
completed | April 15, 2026, 12:07 a.m. |
Created at: April 10, 2026, 2:45 a.m.