ClaimLens is a fact-checking system designed to automatically verify voting-related factual claims in a structured, explainable manner. We extract structured factual claim information using a state-of-the-art frame-semantic parsing (FSP)machine learning model. This structured information, containing the claimed voting Agent, Issue, Position, and many more elements, is fact-checked against a public database of official congressional votes. To enable searching for bills based on complex issues, we utilize a machine learning-based semantic similarity model which helps to identify bills based on their semantic meaning. We also provide a user-friendly interface for interacting with the system, allowing users simply input a claim and quickly see how our FSP model extracts the returned congress member, the bills they voted on, and their corresponding votes. This system enables interactive, real-time fact-checking and is our first step towards building a reliable and explainable automated fact-checking system.