Triple
T21943420
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Chang'an dialect |
E541876
|
entity |
| Predicate | prestigeStatus |
P91227
|
FINISHED |
| Object | prestige dialect of Tang dynasty |
—
|
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: prestige dialect of Tang dynasty | Statement: [Chang'an dialect, prestigeStatus, prestige dialect of Tang dynasty]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: prestigeStatus Context triple: [Chang'an dialect, prestigeStatus, prestige dialect of Tang dynasty]
-
A.
isPrestigeLevel
Indicates that an entity possesses a particular status or rank associated with prestige or high standing.
-
B.
isPrestigiousIn
Indicates that an entity is widely recognized and highly regarded for excellence or status within a particular field, domain, or context.
-
C.
prestigeVarietyOf
chosen
Indicates that one variety (such as a dialect, style, or form) is regarded as more socially prestigious or high-status compared to another variety.
-
D.
morePrestigiousThan
Indicates that one entity is regarded as having higher status, esteem, or prestige than another.
-
E.
VIPStatus
Indicates that an entity holds a special or privileged status compared to others, often granting enhanced access, benefits, or priority treatment.
- 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_69e0c47e2e5c81909a7f74ce3de50911 |
completed | April 16, 2026, 11:14 a.m. |
| NER | Named-entity recognition | batch_69f1242515ec8190b015bf8c7b13be85 |
completed | April 28, 2026, 9:18 p.m. |
| PD | Predicate disambiguation | batch_69e6f5efc208819091ed2cf6841fa600 |
completed | April 21, 2026, 3:58 a.m. |
Created at: April 16, 2026, 7:56 p.m.