While the volume and diversity of multimedia permeating the world around us increases, our chances of making sense of the available information do the opposite. This environment poses a number of challenges which include achieving scalability while accessing all the available media, live and archived, inferring its context, and delivering media to all interested parties with its context attached. We envision a solution to this set of challenges in a novel system architecture. As a starting point, however, we select a previously described framework, Event-Web [7], suitable for annotating raw multimedia data with context meaningful to end users. We then map it onto a distributed architecture capable of correlating, analyzing, and transporting the volumes of data characteristic of the problem space. This paper first presents the requirements for our architecture, then discusses this architecture in detail, and outlines our current implementation efforts.