SemLAV allows to execute SPARQL queries against the Deep Web and Linked Open Data data sources. It implements the mediator-wrapper architecture based on view definitions over remote data sources. SPARQL queries are expressed using a mediator schema vocabulary, and SemLAV selects relevant data sources and rank them. The ranking strat-egy is designed to deliver results quickly based only on view definitions, i.e., no statistics, nor probing on sources are required. In this demonstra-tion, we validate the effectiveness of SemLAV approach with real data sources from social networks and Linked Open Data. We show in differ-ent setups that materializing only a subset of ranked relevant views is enough to deliver significant part of expected results.