Triple
T15268905
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Southern Bavarian |
E364969
|
entity |
| Predicate | hasDialect |
P4251
|
FINISHED |
| Object | Tyrolean |
E17273
|
NE 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: Tyrolean | Statement: [Southern Bavarian, hasDialect, Tyrolean]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Tyrolean Context triple: [Southern Bavarian, hasDialect, Tyrolean]
-
A.
Österreichisch-Weiß
Österreichisch-Weiß is a historical Central European white grape variety known primarily as one of the parent grapes of Silvaner.
-
B.
Western Tyrol
Western Tyrol is a mountainous region in western Austria known for its high Alpine peaks, including the Wildspitze, and popular ski and hiking areas.
-
C.
AUSTRIAN
AUSTRIAN is the radio callsign used by Austrian Airlines, the flag carrier airline of Austria.
-
D.
Ladin language
Ladin language is a Rhaeto-Romance language spoken primarily in the Dolomite mountain region of northern Italy.
-
E.
Austro-Bavarian German
chosen
Austro-Bavarian German is a major Upper German dialect group spoken primarily in Austria and parts of Bavaria and South Tyrol, characterized by distinct phonology, vocabulary, and regional varieties.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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_69d85a0f08408190b3c3259ae35d79d2 |
completed | April 10, 2026, 2:01 a.m. |
| NER | Named-entity recognition | batch_69e0094ca9ac8190a1f97a7b74c96cd5 |
completed | April 15, 2026, 9:55 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69fee602067c81908b1aaaca8871eeb9 |
completed | May 9, 2026, 7:45 a.m. |
Created at: April 10, 2026, 3:14 a.m.