There is an increasing demand for rapid content filtering in relation to topics like digital forensics for legal cases, cybersecurity, and social media conduct monitoring. While there have been significant advances in algorithms and frameworks for media processing, this task requires an ensemble of tools and algorithms that are not well-understood by human analysts, thereby reducing their trustworthiness. In this paper, we present a novel perspective on this problem through the development of an intelligent system that generates reports from large email datasets in the form of short stories. The stories generated by the system are based on identifiable plot structures in popular media. These structures are used as semantic sensemaking templates to organize data for further filtering and triage. The end-to-end system, accessible through an interactive dashboard, incorporates unsupervised annotation modules (such as speech acts and sentiment), topic discovery, communication network analysis, character personality profiles, and automated text and visualization generators. This emerging application prototype is developed and internally deployed in collaboration with analysts and researchers actively working in this area.