[Context and Motivation] To ensure that software is developed as intended, it is important to connect the completion of software development activities with the requirements that they support; yet, establishing traceability links is a costly task. [Problem] Recent work has suggested the use of machine learning and large language models (LLMs) for many software engineering tasks, including traceability. However, there are insufficient publicly available requirements documents to effectively train third-party LLMs and %because of concerns about privacy and intellectual property rights, as well as regulations, uploading proprietary data to be processed by external LLMs may be infeasible due to privacy concerns. %Further, [Principal Idea] To address these challenges, we propose a privacy-preserving pipelined approach combining clustering and triplet loss learning (TLL) to create artifact-to-requirements traceability links. Our clustering method efficiently identifies training examples for TLL, enabling local trace computation with minimal training data. [Contribution] In this research preview, we present our pipelined approach with an initial proof of concept and analyze the use of our clustering strategy. We outline a research agenda with risk mitigation for system validation.