World’s broadcast, print, and web news globally provides near-real-time spatiotemporal information. This information is valuable for extracting geographical locations and associated themes to gain insights into current events. Current tools often lack the ability to make the link between complex variables such as spatial accuracy and contextual references described in media. Many Natural Language Processing (NLP) and Large Language Models (LLMs) using neural network architecture are built to identify diverse sets of co-dependencies and inter-connections between spatial and contextual information. This project aims to better understand large global databases and leverage NLPs and LLMs to categorize media topics, identify-extract spatial locations, catalog date-time of events, and detect spatio-temporal patterns to build dashboards and complex decision-making tools for analysts. The case studies will examine current global conflicts and violence.