Graph Neural Networks (GNNs) are specialized machine learning models designed for working with graph-structured data. They directly operate on graphs, treating nodes as data points and edges as connections. GNNs excel at propagating information between connected nodes, enabling them to capture both local and global context. They create low-dimensional node embeddings that are valuable for various tasks, and often employ a hierarchical approach for learning complex patterns in the data. In essence, GNNs are a valuable tool for analyzing and making predictions based on graph-structured data. In this paper, we introduce a novel approach that utilizes GNN for the analysis of heterogeneous event graphs. Specifically, our primary objective is pattern classification. We focus on events that occur at specific points in time and involve distinct entities within social or physical systems, allowing us to represent them within a network structure. Our proposal is tested and compared with different public dataset.