The classifier LogisticRegressionClassifier.prob returns non-match probability instead of match probability. Is this dataset dependent behavior?

I'd love to see you record a 3 min video added as a link on your README.md might help to quickly understand the scope/applicability/benefits.

Your WHAT statement is not enough for fully understanding the WHY and BENEFIT provided.
I'd suggest to add a continued sentence, "...large-scale third-party catalogs, so that you can ..." to the
"soweego is a pipeline that connects Wikidata to large-sc

Currently, the coverage report that the Azure pipeline is sending to codecov does not seem to include its origin, i.e. that it has been generated from Azure Dev-Ops and where to find information about it.

For example, in this case, I (paa2013) made the change. Instead, it would appear Dikoma Shungu did (which is inaccurate).

This information will be useful for reporting purposes.