Event management and response generation are two essential aspects of systems for Ambient Intelligence. In this regard, the context notion does also play an essential role, not only in determining the set of activities that take place in it, but also in devising the most appropriate response to those situations. Context is also essential for disambiguating knowledge and meaning. This work therefore proposes handling these issues by means of an approach with which to model and reason about actions and events which, under the umbrella of a philosophical and common-sense point of view, describes what actions and events are, how they are connected, and how computational systems should consider their meaning. Actions and events occur in the frame of situations. In order to leverage Ambient Intelligence systems to autonomously manage their environment these situations need to be characterized and understood. This work also describe an approach to tackle this challenge.