Services need to adapt themselves to their computing environment and the situation of the user to be Context-Aware Services (CASs). For their adaptation, they are in need of specific context information, that often has to be derived from other pieces of low-level context information. The process of retrieving context information is highly dynamic since appropriate context sources are often unknown at design time and need to be discovered and understood at runtime. This paper proposes the CoCo concept (Context Composition) that consists of key infrastructural components supporting the process of context retrieval and context composition, and a graph-oriented language describing the steps that need to be executed to compose context information. CoCo needs an information model specifying the semantics of the information. CoCo is able to automate the process of context retrieving — even in heterogenous environments — to simplify the development and deployment of CASs and to increase their robustness.