Triple
T12718736
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Cologne Dada |
E303916
|
entity |
| Predicate | locatedIn |
P40
|
FINISHED |
| Object | Cologne, Germany |
E35950
|
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: Cologne, Germany | Statement: [Cologne Dada, locatedIn, Cologne, Germany]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Cologne, Germany Context triple: [Cologne Dada, locatedIn, Cologne, Germany]
-
A.
Cologne
chosen
Cologne is a historic German city on the Rhine River, renowned for its Gothic cathedral, vibrant cultural scene, and status as a major economic and media hub.
-
B.
Krefeld, Germany
Krefeld, Germany is an industrial city in North Rhine-Westphalia known historically for its textile and silk production.
-
C.
Frankfort, Germany
Frankfort, Germany is a German city whose name has been used for places abroad, including the village of Frankfort in Illinois, USA.
-
D.
Brühl, Germany
Brühl, Germany is a town in North Rhine-Westphalia known for its UNESCO-listed Augustusburg and Falkenlust palaces and its proximity to Cologne.
-
E.
Hamm, Germany
Hamm is a city in the German state of North Rhine-Westphalia, known as an industrial and transportation hub in the eastern Ruhr 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_69d7bdf084148190ab9d513dc0735af4 |
completed | April 9, 2026, 2:55 p.m. |
| NER | Named-entity recognition | batch_69d9625d9da48190ab377f9328a0e1f5 |
completed | April 10, 2026, 8:49 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f68eb1ca1081909b2e9e70f6a497dd |
completed | May 2, 2026, 11:54 p.m. |
Created at: April 9, 2026, 5:24 p.m.