Triple
T19623828
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Fujiwara no Hidehira |
E471081
|
entity |
| Predicate | associatedWith |
P37
|
FINISHED |
| Object | Mōtsū-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: Mōtsū-ji | Statement: [Fujiwara no Hidehira, associatedWith, Mōtsū-ji]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Mōtsū-ji Context triple: [Fujiwara no Hidehira, associatedWith, Mōtsū-ji]
-
A.
Mōtsū-ji
chosen
Mōtsū-ji is a historic Tendai Buddhist temple complex in Hiraizumi, Japan, renowned for its Pure Land garden and association with the powerful Northern Fujiwara clan.
-
B.
Hotsumisaki-ji
Hotsumisaki-ji is a Buddhist temple in Kōchi Prefecture, Japan, known as Temple 24 on the Shikoku Pilgrimage.
-
C.
Shomyoji Temple
Shomyoji Temple is a historic Buddhist temple in Yokohama’s Kanazawa area, known for its scenic garden, arched bridge, and tranquil pond.
-
D.
Myokoku-ji Temple
Myokoku-ji Temple is a historic Buddhist temple in Sakai, Osaka, known for its traditional architecture and cultural significance.
-
E.
Enmyō-ji
Enmyō-ji is a Buddhist temple in Japan best known as Temple 53 on the Shikoku Pilgrimage.
- 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_69d8e510fa248190b7afb274a1d4cf73 |
completed | April 10, 2026, 11:54 a.m. |
| NER | Named-entity recognition | batch_69e640e8695c81909268c5a91cdbb7fa |
completed | April 20, 2026, 3:06 p.m. |
Created at: April 10, 2026, 1:44 p.m.