Triple
T22024767
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Yumedono |
E543931
|
entity |
| Predicate | nativeName |
P15
|
FINISHED |
| Object | 夢殿 |
—
|
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: 夢殿 | Statement: [Yumedono, nativeName, 夢殿]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: 夢殿 Context triple: [Yumedono, nativeName, 夢殿]
-
A.
銀閣
銀閣 is the Japanese name for the famed Silver Pavilion at Kyoto’s Ginkaku-ji Zen temple, renowned for its elegant architecture and serene gardens.
-
B.
Yumedono (Hall of Dreams)
chosen
Yumedono (Hall of Dreams) is a renowned octagonal hall within the Hōryū-ji temple complex in Nara, Japan, celebrated for its historic Buddhist statues and association with Prince Shōtoku.
-
C.
Manoir de mes rêves
"Manoir de mes rêves" is a lyrical jazz composition by guitarist Django Reinhardt, showcasing his melodic sensitivity and romantic side within the Gypsy jazz tradition.
-
D.
House under the Starry Sky
House under the Starry Sky is a film directed by Russian filmmaker Sergey Solovyov.
-
E.
皇霊殿
皇霊殿は、歴代天皇や皇族の霊を祀るために皇居内に設けられた皇室の重要な祭祀施設である。
- 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_69e11e2e8ea4819084210fe06d3a1b8d |
completed | April 16, 2026, 5:36 p.m. |
| NER | Named-entity recognition | batch_69f127ca45a08190b2d5d3a8eb37cb4b |
completed | April 28, 2026, 9:34 p.m. |
Created at: April 16, 2026, 8:23 p.m.