Knowledge-based solutions for text generation are known to produce outputs that usually sound repetitive and stilted to the human ear. Attention-based neural solutions for generating text have proven to be successful at generating unconstrained prose that is fluent and sounds natural, but they have difficulty in producing texts that comply with a set of restrictions provided as input. The present paper explores combinations of a knowledge-based content generator and a neural text realizer, focusing on how creative responsibility over the final output is distributed over the knowledge-based and the neural modules of the system. A conceptual draft for a story is produced by a knowledge-based solution. The stories are then told using neural generators, with different types of prompt being built as means of requesting specific ways of telling the selected events. The outcomes are evaluated in terms of the percentage of the ideas in the final text that have been contributed by each module.