We present the architecture and the evaluation of a new system for recognizing textual entailment (RTE). In RTE we want to identify automatically the type of a logical relation between two input texts. In particular, we are interested in proving the existence of an entailment between them. We conceive our system as a modular environment allowing for a high-coverage syntactic and semantic text analysis combined with logical inference. For the syntactic and semantic analysis we combine a deep semantic analysis with a shallow one supported by statistical models in order to increase the quality and the accuracy of results. For RTE we use logical inference of first-order employing model-theoretic techniques and automated reasoning tools. The inference is supported with problem-relevant background knowledge extracted automatically and on demand from external sources like, e.g., WordNet, YAGO, and OpenCyc, or other, more experimental sources with, e.g., manually defined presupposition resolutions, or with axiomatized general and common sense knowledge. The results show that fine-grained and consistent knowledge coming from diverse sources is a necessary condition determining the correctness and traceability of results.