Triple
T14482228
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Walser German dialects |
E359133
|
entity |
| Predicate | hasDialect |
P4251
|
FINISHED |
| Object | Formazza German |
E619935
|
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: Formazza German | Statement: [Walser German dialects, hasDialect, Formazza German]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Formazza German Context triple: [Walser German dialects, hasDialect, Formazza German]
-
A.
Formazza
chosen
Formazza is a mountainous Italian municipality in the Piedmont region, known for its alpine landscapes, waterfalls, and Walser cultural heritage.
-
B.
Wartmannsroth
Wartmannsroth is a small municipality in the Lower Franconia region of Bavaria, Germany, known for its rural character and scenic surroundings.
-
C.
Frankfurter
Frankfurter is a Jewish Ashkenazi toponymic surname originally denoting a person from the city of Frankfurt in Germany.
-
D.
Colognian
Colognian is a Central Ripuarian Franconian dialect of German spoken primarily in and around the city of Cologne.
-
E.
Roitzsch
Roitzsch is a village-level subdivision of the town of Wurzen in the Free State of Saxony, Germany.
- 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_69d827966698819082e140837737501d |
completed | April 9, 2026, 10:26 p.m. |
| NER | Named-entity recognition | batch_69de924bc548819087a2f693840d7426 |
completed | April 14, 2026, 7:15 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69fd64a41a8c819081a3eaabbe66577a |
completed | May 8, 2026, 4:20 a.m. |
Created at: April 10, 2026, 1:20 a.m.