Natural products such as medicinal plants and extract mixtures have successfully supported the discovery of pharmaceuticals. Medically relevant products and their properties are often found through systematic analysis of the literature. In 1980s Swanson found hidden links between pieces of knowledge in the scientific literature by a manual algorithm, hinting that literature based discovery (LBD) can be automated. Swanson formulated clinically relevant hypotheses which were confirmed in trials. LBD has become widespread, but little has been done to automate it in the field of Natural Product Drug Discovery. Today manual text mining is common practice in this field, but it is extremely laborious and time-consuming. Semantic Web technology is ideal for automating LBD. Yet, no LBD system has adopted it in an integrated approach. It builds on semantic atomic data entities, so called subject-predicate object triples. Terms in triples can be mapped to ontologies, which define a common vocabulary, machine interpretable concepts and logic based relations. The biomedical community has been very active in ontology development. We propose to devise an automated LBD system for natural product drugs, using Semantic Web technologies. Our system can be used not only for new discoveries, but also to query and explore present knowledge. Further, it reduces discovery costs by saving time in evaluating literature for drug development, but is also relevant to safety and pharmacovigilance aspects.