We analyse the requirements for an advanced semantic sup- port of users—building historians and architects—of a multi-volume en- cyclopedia of architecture from the late 19 th century. Novel requirements include the integration of content retrieval, content development, and au- tomated content analysis based on natural language processing. We present a system architecture for the detected requirements and its current implementation. A complex scenario demonstrates how a desktop supporting semantic analysis can contribute to specific, relevant user tasks.