Software testing is a core discipline in software engineering where a large array of research results has been produced, notably in automatic test generation. However, the resulting test suits are often incomplete and can be qualified as simple (e.g. unit tests): they only cover parts of the project or they are produced after the bug is fixed and therefore can only serve as regression tests. Yet, several research challenges, such as automatic program repair, build on the assumption that available test suites are sufficient. There is thus a need to break existing barriers in automatic test case generation. While prior work largely focused on random unit testing inputs, we propose to consider generating test cases that realistically represent complex user execution scenarios, which reveal buggy behaviour. Such scenarios are informally described in bug reports, which should therefore be considered as natural inputs for specifying bug-triggering test cases. In this work, we investigate the feasibility of performing this generation by leveraging large language models (LLMs) and using bug reports as inputs. Our experiments consider various settings, including the use of ChatGPT, as an online service for accessing an LLM, as well as CodeGPT, an existing code-related pre-trained LLM that was fine-tuned for our task. Our study is carried out on the Defects4J dataset. Overall, we experimentally show that bug reports associated to up to 50% of Defects4J bugs can prompt ChatGPT to generate an executable test case. We show that even new bug reports (i.e., previously-unseen data to mitigate data leakage threat to validity), can indeed be used as input for generating the executable test cases.