Triple
T2963023
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Erlangen |
E80092
|
entity |
| Predicate | locatedOn |
P40
|
FINISHED |
| Object | Regnitz River |
E124915
|
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: Regnitz River | Statement: [Erlangen, locatedOn, Regnitz River]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Regnitz River Context triple: [Erlangen, locatedOn, Regnitz River]
-
A.
Regnitz
chosen
The Regnitz is a river in the German state of Bavaria that flows through cities such as Erlangen and Bamberg before joining the Main River.
-
B.
Würm River
The Würm River is a small river in Bavaria, Germany, known for flowing north from Lake Starnberg through towns such as Gauting and Starnberg before joining the Amper River.
-
C.
Saale
The Saale is a major river in central Germany that flows through the states of Thuringia, Saxony-Anhalt, and Bavaria before joining the Elbe.
-
D.
Wupper
The Wupper is a river in North Rhine-Westphalia, Germany, known for flowing through the industrial city of Wuppertal and its surrounding region.
-
E.
Rüdnitz
Rüdnitz is a small municipality in the Barnim district of the federal state of Brandenburg in northeastern Germany.
- 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_69ad8b1341848190bd19dbf46892887d |
completed | March 8, 2026, 2:43 p.m. |
| NER | Named-entity recognition | batch_69ad9957602c819089b673966fd619e0 |
completed | March 8, 2026, 3:44 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b4dae657ec81909e8a99e4ccd95bfc |
completed | March 14, 2026, 3:49 a.m. |
Created at: March 8, 2026, 2:57 p.m.