Abstract: A device may generate, from a subset of historical ontology data and a substance description of a substance, a knowledge base. The subset of historical ontology data may be associated with historical substances. The device may generate, based on the knowledge base, a substance knowledge graph embedding (KGE) that is representative of the substance; compare the substance KGE and a historical KGE associated with the knowledge base; determine, based on comparing the substance KGE and the historical KGE, a similarity score associated with the substance KGE and the historical KGE; determine, based on the similarity score, whether substance data associated with a related substance is similarly represented in the substance KGE and the historical KGE; and perform, based on whether the substance data is similarly represented in the substance KGE and the historical KGE, an action associated with the related substance relative to the substance description or the knowledge base.