Triple
T7323593
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Lutherstadt Wittenberg station |
E168811
|
entity |
| Predicate | connectsTo |
P845
|
FINISHED |
| Object | Dessau |
E102721
|
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: Dessau | Statement: [Lutherstadt Wittenberg station, connectsTo, Dessau]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Dessau Context triple: [Lutherstadt Wittenberg station, connectsTo, Dessau]
-
A.
Dessau
chosen
Dessau is a German city best known for its association with the Bauhaus movement and its iconic modernist architecture.
-
B.
Oranienburg
Oranienburg is a town in Brandenburg, Germany, historically known as the site of the Nazi Sachsenhausen concentration camp.
-
C.
Degendorf
Degendorf is a locality within the Bavarian town and district of Lichtenfels in Germany.
-
D.
Sangerhausen
Sangerhausen is a town in the German state of Saxony-Anhalt, known for its historic mining heritage and its renowned Europa-Rosarium rose garden.
-
E.
Zerbst
Zerbst is a historic town in Saxony-Anhalt, Germany, known as the birthplace of Catherine the Great and for its former role as a princely residence.
- 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_69c68a54cacc81908e3b773441f19566 |
completed | March 27, 2026, 1:47 p.m. |
| NER | Named-entity recognition | batch_69c6f046b93c8190a80dd48ee409ec5d |
completed | March 27, 2026, 9:01 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c86130228c819098544e5354c31b44 |
completed | March 28, 2026, 11:16 p.m. |
Created at: March 27, 2026, 3:03 p.m.