Triple
T8862532
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Wettin-Löbejün |
E210926
|
entity |
| Predicate | formedByMergerOf |
P77
|
FINISHED |
| Object | Löbejün |
E762234
|
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: Löbejün | Statement: [Wettin-Löbejün, formedByMergerOf, Löbejün]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Löbejün Context triple: [Wettin-Löbejün, formedByMergerOf, Löbejün]
-
A.
Löbejün
chosen
Löbejün is a small town in the German state of Saxony-Anhalt, known for its historic architecture and location within the municipality of Wettin-Löbejün.
-
B.
Röcken
Röcken is a small village in Saxony-Anhalt, Germany, best known as the birthplace of the philosopher Friedrich Nietzsche.
-
C.
Jülich-Berg
Jülich-Berg was a historical duchy in the Holy Roman Empire located in what is now western Germany, formed by the union of the territories of Jülich and Berg.
-
D.
Hangelsberg
Hangelsberg is a village in the German state of Brandenburg, known as a district of the municipality Grünheide (Mark) in the Oder-Spree region.
-
E.
Hochsölden
Hochsölden is a small alpine ski resort village in the Austrian Tyrol, known for its high-altitude slopes and direct access to the larger Sölden ski area.
- 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_69ca838bbddc8190ab546d737e5d350f |
completed | March 30, 2026, 2:07 p.m. |
| NER | Named-entity recognition | batch_69cc610263048190931bb2c3ac573a08 |
completed | April 1, 2026, 12:04 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69cfab8fef348190a25e978085e8e656 |
completed | April 3, 2026, 11:59 a.m. |
Created at: March 30, 2026, 6:50 p.m.