Triple
T31443900
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Qiongzhou dialect |
E802138
|
entity |
| Predicate | competingLanguage |
P41297
|
FINISHED |
| Object | Mandarin Chinese |
—
|
NE NERFINISHED |
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: Mandarin Chinese | Statement: [Qiongzhou dialect, competingLanguage, Mandarin Chinese]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: competingLanguage Context triple: [Qiongzhou dialect, competingLanguage, Mandarin Chinese]
-
A.
languageUsedByOpponents
Indicates that a particular language is used by entities who are opponents in some context (e.g., conflict, competition, or rivalry).
-
B.
coexistsWithLanguage
chosen
Indicates that one entity exists or functions alongside a particular language at the same time, without excluding or replacing it.
-
C.
recognizedAsDistinctLanguageFrom
Indicates that one language is formally acknowledged or treated as a separate and distinct language from another, rather than as a dialect or variant of it.
-
D.
hasLanguageSimilarTo
Indicates that one entity uses or is associated with a language that is similar or closely related to the language used or associated with another entity.
-
E.
usesWorkingLanguagesOf
Indicates that one entity employs or operates using the working languages 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_69f348c5a6bc819092a557e95438976f |
completed | April 30, 2026, 12:19 p.m. |
| NER | Named-entity recognition | batch_69f7465687bc8190a9da44d62b634ed7 |
completed | May 3, 2026, 12:57 p.m. |
| PD | Predicate disambiguation | batch_69f743f4ceb08190a21fe7f4a99b166b |
completed | May 3, 2026, 12:47 p.m. |
Created at: April 30, 2026, 9:08 p.m.