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.