Triple
T24839626
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Zagreb region |
E621578
|
entity |
| Predicate | usesDialectGroup |
P142293
|
FINISHED |
| Object | Kajkavian dialect group |
—
|
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: Kajkavian dialect group | Statement: [Zagreb region, usesDialectGroup, Kajkavian dialect group]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: usesDialectGroup Context triple: [Zagreb region, usesDialectGroup, Kajkavian dialect group]
-
A.
usesDialect
Indicates that one entity communicates or expresses itself using the specific dialect associated with another entity.
-
B.
isDialectGroupOf
Indicates that one linguistic variety is a dialect group or cluster belonging to a broader language or language family.
-
C.
associatedWithDialectGroup
chosen
Indicates that one entity is connected or related to a particular dialect group, typically through usage, origin, or classification.
-
D.
commonInDialectGroup
Indicates that something (such as a word, form, or feature) is frequently used or widely found within a particular dialect group.
-
E.
hasDialects
Indicates that an entity (typically a language) possesses one or more distinct dialectal varieties.
- 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_69e2fac185d48190a0a6073ad1f6b792 |
completed | April 18, 2026, 3:30 a.m. |
| NER | Named-entity recognition | batch_69f453035f508190be83a3d521723acf |
completed | May 1, 2026, 7:15 a.m. |
| PD | Predicate disambiguation | batch_69f44d6ef33081908f5d36ba1ae5f473 |
completed | May 1, 2026, 6:51 a.m. |
Created at: April 18, 2026, 5:18 a.m.