If you want to solve a multi-class classification problem, you could use the famous iris flower dataset, which was introduced by Fisher in 1936. In this dataset, each flower has (only) $4$ features (the inputs), namely
- petal length,
- petal width,
- sepal length, and
- sepal width
There are $3$ classes (the outputs)
- iris setosa,
- iris virginica, and
- iris versicolor
And there are a total of $150$ observations (or records).
The iris flower dataset is available in
sklearn. See, for example, Iris plants dataset.
To search for other datasets, you can also use https://toolbox.google.com/datasetsearch.