Triple
T19948073
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kasuga-zukuri |
E479480
|
entity |
| Predicate | eaveFeature |
P19771
|
FINISHED |
| Object | deeply overhanging eaves |
—
|
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: deeply overhanging eaves | Statement: [Kasuga-zukuri, eaveFeature, deeply overhanging eaves]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: eaveFeature Context triple: [Kasuga-zukuri, eaveFeature, deeply overhanging eaves]
-
A.
exteriorFeature
chosen
Indicates a relationship where one entity serves as an external or outward-facing feature, element, or characteristic of another entity.
-
B.
elevatedFeature
Indicates that one feature or element is positioned or raised higher relative to another reference level or surrounding context.
-
C.
featuresIn
Indicates that an entity appears or plays a role within another entity, such as a person or element being included in a work, event, or context.
-
D.
nestFeature
Indicates that one entity is a structural or functional component contained within, or forming part of, another entity.
-
E.
eve
Indicates a relationship where one entity is the evening or night-time counterpart, phase, or occurrence associated with another entity.
- F. None of above.
Provenance (3 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_69d8e522a17c819095165d4d24939fd8 |
completed | April 10, 2026, 11:55 a.m. |
| NER | Named-entity recognition | batch_69e65a69ae388190918e862012f9fe39 |
completed | April 20, 2026, 4:55 p.m. |
| PD | Predicate disambiguation | batch_69e537f47c508190853c4e009c6b5566 |
completed | April 19, 2026, 8:15 p.m. |
Created at: April 10, 2026, 1:54 p.m.