In this paper we propose a new shared task where the aim is to produce coherent descriptions of concepts and relationships in a frame-based knowledge base (KB). We propose to use AURA, a freely available KB, for the shared task and illustrate an application context for NLG. We show that the same application context and the need for language generation tools can be generalized to other biology knowledge bases. We argue that the easy availability of input data and a larger research community -- both domain experts and knowledge representation experts -- which actively uses these knowledge bases, along with regular evaluation experiments, creates an ideal scenario for a shared task.