This paper presents a novel approach to automating ontology generation in the field of systems engineering using the Lifecycle Modeling Language (LML) as a case study. By applying natural language processing (NLP) techniques—specifically part-of-speech tagging through Python scripts—researchers extracted hundreds of classes and object properties from the LML v1.4 specification, producing an ontology with approximately 14,000 axioms and over 115,000 RDF triples. This process bridges the gap between manual ontology development and scalable, AI-driven solutions, enhancing semantic clarity, consistency, and reusability across engineering tools. The methodology demonstrates the potential for significantly accelerating ontology creation, fostering improved data integration, and supporting more robust model-based systems engineering practices.