Triple
T16732082
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Anhalt Railway |
E406615
|
entity |
| Predicate | connects |
P390
|
FINISHED |
| Object | Köthen |
—
|
NE NERFINISHED |
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: Köthen | Statement: [Anhalt Railway, connects, Köthen]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Köthen Context triple: [Anhalt Railway, connects, Köthen]
-
A.
Köthen
chosen
Köthen is a town in the German state of Saxony-Anhalt, historically known as the residence of the Princes of Anhalt and as a significant center of Baroque music, including Johann Sebastian Bach’s tenure there.
-
B.
Rudolstadt
Rudolstadt is a historic town in the German state of Thuringia, known for its picturesque old town, Heidecksburg Castle, and cultural festivals.
-
C.
Querfurt
Querfurt is a small historic town in the German state of Saxony-Anhalt, known for its well-preserved medieval castle and old town.
-
D.
Oranienburg
Oranienburg is a town in Brandenburg, Germany, historically known as the site of the Nazi Sachsenhausen concentration camp.
-
E.
Hoyerswerda
Hoyerswerda is a town in eastern Germany’s Saxony region, historically shaped by lignite mining and now known for its proximity to the emerging Lusatian lake landscape.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69d8838f242881908abd8bc138795886 |
completed | April 10, 2026, 4:58 a.m. |
| NER | Named-entity recognition | batch_69e39c362bb88190921fab43d76c3ee8 |
completed | April 18, 2026, 2:59 p.m. |
Created at: April 10, 2026, 5:20 a.m.