Junoš Lukan, Maori Inagawa and Mitja Lustrek

Abstract
Waste Quantification Solutions to Limit Environmental
Stress (WASTELESS) project aims to develop and test
innovative tools and methodologies for measuring and monitoring
food loss and waste (FLW). A key objective is to
create a decision support toolbox that helps food actors
across the entire supply chain, including consumers, select
the most suitable method for measuring and monitoring
FLW. To help with this decision, existing, already tested
FLW measurement practices can be consulted, which are
currently published as short documents. In this work, we
show how the data about them can be extracted using
large language models (LLMs). Additionally, we propose
how this data can be structured and represented as an
ontology. With this process, we can help users find relevant
data without needing to browse through many documents.