Open data has become increasingly attractive for users, especially companies, due to its value-creating capabilities and innovation potential. One essential challenge is to identify and leverage suitable open datasets that support specific business scenarios as well as strategic data goals. To overcome this challenge, companies need elaborate processes for open data sourcing. To this end, our research aims to develop prescriptive knowledge in the form of a meaningful method for screening, assessing, and preparing open data for use in an enterprise setting. In line with the principles of Action Design Research (ADR), we iteratively develop a method that comprises four phases and is enabled by knowledge graphs and linked data concepts. Our method supports companies in sourcing open data of uncertain data quality in a value-adding and demand-oriented manner, while creating more transparency about its content, licensing, and access conditions. From an academic perspective, our research conceptualizes open data sourcing as a purposeful and value-creating process.