Triple
T3791930
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Röcken |
E89670
|
entity |
| Predicate | partOf |
P40
|
FINISHED |
| Object | Lützen |
E222931
|
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: Lützen | Statement: [Röcken, partOf, Lützen]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Lützen Context triple: [Röcken, partOf, Lützen]
-
A.
Lützen
chosen
Lützen is a town in present-day Germany best known as the site of the 1632 Battle of Lützen during the Thirty Years' War, where Swedish King Gustavus Adolphus was killed.
-
B.
Pegnitz
Pegnitz is a river in the German state of Bavaria that flows through cities such as Nuremberg and Bayreuth before joining the Rednitz to form the Regnitz.
-
C.
Kunersdorf
Kunersdorf is a village in present-day Poland best known as the site of the pivotal 1759 Battle of Kunersdorf during the Seven Years' War.
-
D.
Jena
Jena is a historic university city in the German state of Thuringia, known for its role in optics, philosophy, and science.
-
E.
Battle of Torgau
The Battle of Torgau was a pivotal 1760 engagement of the Seven Years' War in which Frederick the Great’s Prussian army fought the Austrians in one of the conflict’s bloodiest and most tactically complex battles.
- 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_69aed9597d6881909b6ee3b9de859223 |
completed | March 9, 2026, 2:29 p.m. |
| NER | Named-entity recognition | batch_69aee769d68081908dcdd3d232dbb61c |
completed | March 9, 2026, 3:29 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b4f055e3988190a1b3633e390c0d6f |
completed | March 14, 2026, 5:21 a.m. |
Created at: March 9, 2026, 3:15 p.m.