[Context and motivation] Requirements reuse is one of the many techniques that contribute to requirements elicitation. Classical approaches to requirements reuse, such as the use of software requirement patterns (SRPs), require continuous maintenance in order to evolve the embedded knowledge as new problems and domains come into existence. At this respect, the emergence of large language models (LLMs) opens the door to cost-effective strategies to manage such reusable knowledge. Still, the stochastic nature of LLMs threatens the inherent quality of requirements reuse and consequently, that of the elicitation process. [Question/problem] In this scientific evaluation paper, we investigate whether and how LLMs can be used in order to create an SRP catalog and derive requirements from it. We take chatGPT 4o as LLM and PABRE as SRP-based approach to requirements reuse. [Principal ideas/results] We show that SRPs can be effectively extracted by querying an LLM through appropriate prompts, with manual consolidation of multiple runs yielding the best results. On the other hand, we also show that LLM-driven generation of questions to stakeholders for eliciting requirements from these SRPs is feasible but suffers from deficiencies such as excessive number of repetitions and out of scope requirements. [Contribution] Our work hints that (1) LLMs can be embedded into the requirements elicitation process through a reuse-based strategy, but at the same time (2) the current state of such technology requires human assessment at a large extent.