Triple
T19346186
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Zentsū-ji Temple |
E483883
|
entity |
| Predicate | hasSubcomplex |
P25619
|
FINISHED |
| Object | Tanjo-in |
—
|
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: Tanjo-in | Statement: [Zentsū-ji Temple, hasSubcomplex, Tanjo-in]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Tanjo-in Context triple: [Zentsū-ji Temple, hasSubcomplex, Tanjo-in]
-
A.
Tanjo-in
chosen
Tanjo-in is a subcomplex of the historic Zentsūji Temple, part of the Shikoku Pilgrimage, traditionally associated with the birthplace and early life of the Buddhist monk Kūkai.
-
B.
Owakudani
Owakudani is a volcanic valley in Hakone, Japan, famous for its active sulfur vents, hot springs, and scenic views of Mount Fuji.
-
C.
Gokenzan
Gokenzan is the mountain in Kagawa Prefecture on which Temple 84, Yashimaji, of the Shikoku Pilgrimage is located.
-
D.
Sengan-en
Sengan-en is a historic Japanese garden and former Shimazu clan villa in Kagoshima, renowned for its scenic views of Sakurajima and traditional landscape design.
-
E.
Ichi-no-Tani
Ichi-no-Tani was a fortified Taira stronghold near present-day Kobe, Japan, best known as the site of a pivotal 1184 battle during the Genpei War.
- 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_69d8e8d244f8819080eb1f3491300db2 |
completed | April 10, 2026, 12:10 p.m. |
| NER | Named-entity recognition | batch_69e6185b7d348190ba195056bb32c765 |
completed | April 20, 2026, 12:13 p.m. |
Created at: April 10, 2026, 1:34 p.m.