When transforming amounts of plain text into semantic knowledge graphs using Resource Description Framework, a service for automatic interpretation became apparent. Manual interpretation of text depends on human domain knowledge and discovery of entities and relationships in the text. This process is a highly time consuming activity with a risk of misinterpretation. Based on the hypothesis that using Natural Language Processing techniques we can extract information and meaning from text faster than a human being, we successfully implemented a service for automatic metadata and ontology generation for a client in Norwegian public sector. This presentation will walk you through our hypothesis, the steps from text to RDF through Natural Language Processing, and our results.