Triple
T20145507
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 元興寺 |
E491291
|
entity |
| Predicate | 国宝 |
P65971
|
FINISHED |
| Object | 元興寺極楽坊本堂屋根瓦の一部（飛鳥時代瓦） |
—
|
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: 元興寺極楽坊本堂屋根瓦の一部（飛鳥時代瓦） | Statement: [元興寺, 国宝, 元興寺極楽坊本堂屋根瓦の一部（飛鳥時代瓦）]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: 国宝 Context triple: [元興寺, 国宝, 元興寺極楽坊本堂屋根瓦の一部（飛鳥時代瓦）]
-
A.
名物
Indicates that something is a famous local specialty or notable product strongly associated with a particular place.
-
B.
国
Indicates that the subject entity operates within, belongs to, or is associated with the specified country.
-
C.
Xiaoerjing
Indicates a relationship where something is written, represented, or transcribed using the Xiaoerjing (Arabic-based) script for Sinitic languages.
-
D.
Wang Ben
Indicates a relationship or action involving an entity named "Wang Ben," such as authorship, participation, or association, depending on the specific context in which the predicate is used.
-
E.
designatedAsNationalTreasureBy
chosen
Indicates that an entity has been officially recognized and declared a national treasure by a specific authority or country.
- 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_69da6265f8f0819080b29c752a574088 |
completed | April 11, 2026, 3:01 p.m. |
| NER | Named-entity recognition | batch_69e6679e43a48190b3a5da5710b07ff7 |
completed | April 20, 2026, 5:51 p.m. |
| PD | Predicate disambiguation | batch_69e54cfb0d0081908e789b9b57e96668 |
completed | April 19, 2026, 9:45 p.m. |
Created at: April 11, 2026, 11:33 p.m.