The Web has empowered emergency services to enhance operations by collecting real-time information about incidents from diverse data sources such as social media. However, the high volume of unstructured data from the heterogeneous sources with varying degrees of veracity challenges the timely extraction and integration of relevant information to summarize the current situation. Existing work on event detection and summarization on social media relates to this challenge of timely extraction of information during an evolving event. However, it is limited in both integrating incomplete information from diverse sources and using the integrated information to dynamically infer knowledge representation of the situation that captures optimal actions (e.g., allocate available finite ambulances to incident regions). In this paper, we present a novel concept of an Uncertain Concept Graph (UCG) that is capable of representing dynamic knowledge of a disaster event from heterogeneous data sources, particularly for the regions of interest, and resources/services required. The information sources, incident regions, and resources (e.g., ambulances) are represented as nodes in UCG, while the edges represent the weighted relationships between these nodes. We then propose a solution for probabilistic edge inference between nodes in UCG. We model a novel optimization problem for the edge assignment between a service resource to a region node over time trajectory. The output of such structured summarization over time can be valuable for modeling event dynamics in the real world beyond emergency management, across different smart city operations such as transportation.