Triple
T15476402
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 龍山寺 |
E376790
|
entity |
| Predicate | 特色 |
P108397
|
FINISHED |
| Object | 雕梁畫棟 |
—
|
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: 雕梁畫棟 | Statement: [龍山寺, 特色, 雕梁畫棟]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: 特色 Context triple: [龍山寺, 特色, 雕梁畫棟]
-
A.
性格
Indicates a relationship where one entity’s personality, character, or temperament is being described, attributed, or characterized in relation to that entity.
-
B.
性質
chosen
Indicates a characteristic or inherent quality that an entity possesses.
-
C.
cultureCharacteristic
Indicates that a particular trait, practice, or feature is a defining characteristic of a given culture.
-
D.
themeCharacteristic
Indicates that a characteristic, quality, or property is attributed to or associated with a particular theme.
-
E.
tourismCharacteristic
Indicates that something has a specific feature, quality, or attribute relevant to tourism, such as what makes a place, service, or activity notable or suitable for tourists.
- 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_69d85cd21dcc81908646251b1c26ea00 |
completed | April 10, 2026, 2:13 a.m. |
| NER | Named-entity recognition | batch_69e03f88a5dc8190a2d7830748e29180 |
completed | April 16, 2026, 1:46 a.m. |
| PD | Predicate disambiguation | batch_69ded2874b788190999158e0f043be21 |
completed | April 14, 2026, 11:49 p.m. |
Created at: April 10, 2026, 3:34 a.m.