Triple
T13972416
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Bernkastel-Kues |
E336097
|
entity |
| Predicate | hasPart |
P35
|
FINISHED |
| Object | Bernkastel |
E1075158
|
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: Bernkastel | Statement: [Bernkastel-Kues, hasPart, Bernkastel]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Bernkastel Context triple: [Bernkastel-Kues, hasPart, Bernkastel]
-
A.
Bernkastel-Kues
Bernkastel-Kues is a historic wine-growing town in Germany’s Rhineland-Palatinate region, renowned for its medieval architecture and picturesque setting amid the Moselle Valley vineyards.
-
B.
Bernkastel-Wittlich
chosen
Bernkastel-Wittlich is a rural district in the German state of Rhineland-Palatinate, known for its wine-growing regions along the Moselle River and historic towns.
-
C.
Alfter
Alfter is a municipality in western Germany located near Bonn in the state of North Rhine-Westphalia.
-
D.
Geisenheim
Geisenheim is a German town in the Rheingau wine region, known for its viticulture, wine production, and renowned university of applied sciences for wine and horticulture.
-
E.
Ahrweiler
Ahrweiler is a district in the German state of Rhineland-Palatinate, known for its wine-growing Ahr Valley and historic towns.
- 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_69d81c61f3508190aaf2ca0dc0002c59 |
completed | April 9, 2026, 9:38 p.m. |
| NER | Named-entity recognition | batch_69de2e8eae40819080dd4bd25c73b6d6 |
completed | April 14, 2026, 12:09 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69fcb6504dcc81908a1dfa5a83ed7b08 |
completed | May 7, 2026, 3:57 p.m. |
Created at: April 9, 2026, 10:18 p.m.