Open government data refers to data that is made available by government entities to be freely reused by anyone and for any purpose. The potential benefits of open government data are numerous and include increasing transparency and accountability, enhancing citizens' quality of life, and boosting innovation. However, realizing these benefits is not always straightforward, as the usage of this raw data often faces challenges related to its format, structure, and heterogeneity which hinder its processability and integration. In response to these challenges, we propose an approach to maximize the usage of open government data and achieve its potential benefits. This approach leverages knowledge graphs to extract value from open government data and drive the construction of a knowledge graph from structured, semi-structured, and non-structured formats. It involves the extraction, transformation, semantic enrichment, and integration of heterogeneous open government data sources into an integrated and semantically enhanced knowledge graph. Learning mechanisms and ontologies are used to efficiently construct the knowledge graph. We evaluate the effectiveness of the approach using real-world public procurement data and show that it can detect potential fraud such as favoritism.