Triple
T2562523
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Guoyu |
E57273
|
entity |
| Predicate | grammarBasedOn |
P13370
|
FINISHED |
| Object | northern Mandarin dialects |
—
|
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: northern Mandarin dialects | Statement: [Guoyu, grammarBasedOn, northern Mandarin dialects]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: grammarBasedOn Context triple: [Guoyu, grammarBasedOn, northern Mandarin dialects]
-
A.
syntaxBasedOn
Indicates that the syntactic structure or rules of one entity are derived from, influenced by, or constructed according to the syntax of another entity.
-
B.
hasGrammar
Indicates that an entity possesses, follows, or is associated with a particular system of grammatical rules or structure.
-
C.
primaryGrammaticalBasis
chosen
Indicates that one element serves as the main grammatical foundation or core structure upon which another linguistic element is based or constructed.
-
D.
grammaticalStructure
Indicates the way linguistic elements are organized and related within a sentence or phrase according to grammatical rules.
-
E.
basedOnText
Indicates that something is derived, adapted, or developed from a specific text source.
- 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_69ab4a4ef9008190a0e6d4422b9418b7 |
completed | March 6, 2026, 9:42 p.m. |
| NER | Named-entity recognition | batch_69abd35c6ee88190b6eaa1841d3e99a4 |
completed | March 7, 2026, 7:27 a.m. |
| PD | Predicate disambiguation | batch_69abd0caeb488190b0dd8e48d0f2777d |
completed | March 7, 2026, 7:16 a.m. |
Created at: March 6, 2026, 9:48 p.m.