Modeling of a business system has traditionally been based on free text documents. This work describes an elaborate experiment that constitutes a proof of concept to the idea that a system model can be acquired through an automated process whose input is a corpus of technical free text requirement documents and whose output is an OPM model, expressed both graphically, through a set of Object-Process Diagrams, and textually in equivalent ObjectProcess Language. Our experiment has yielded a high quality system model that required a much smaller effort than what would have been needed in the traditional approach.