Triple
T12696976
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Rokuon-ji |
E303358
|
entity |
| Predicate | groundFloorStyleOfKinkaku |
P106392
|
FINISHED |
| Object | Shinden-zukuri palace style |
—
|
LITERAL 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: Shinden-zukuri palace style | Statement: [Rokuon-ji, groundFloorStyleOfKinkaku, Shinden-zukuri palace style]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: groundFloorStyleOfKinkaku Context triple: [Rokuon-ji, groundFloorStyleOfKinkaku, Shinden-zukuri palace style]
-
A.
honkanStyle
Indicates a relationship where something follows or exhibits the characteristics of the Honkan style (a specific stylistic or design convention).
-
B.
typicalShrineFeature
Indicates that something is a characteristic or commonly found element of a shrine.
-
C.
hillTemple
Indicates a relationship where a temple is located on, associated with, or dedicated to a hill.
-
D.
AtsutaShrineIs
Indicates that something has the status, identity, or defining characteristics of Atsuta Shrine.
-
E.
shrineType
Indicates the specific category or kind of shrine associated with an entity.
- F. None of above. chosen
Provenance (4 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_69d7bdef90d48190b46b88270e780946 |
completed | April 9, 2026, 2:55 p.m. |
| NER | Named-entity recognition | batch_69d962a32c6481908ddaddae4ea267bf |
completed | April 10, 2026, 8:50 p.m. |
| PD | Predicate disambiguation | batch_69d960be63f081908a5ef5ef17a311bf |
completed | April 10, 2026, 8:42 p.m. |
| PDg | Predicate description generation | batch_69d96297b81c819081ad1432dc5f15f4 |
completed | April 10, 2026, 8:50 p.m. |
Created at: April 9, 2026, 5:22 p.m.