Problem:
A supervisor presents you with a problem. They need to extract key information from PDF incident reports and understand what characteristics of incidents lead to successful resolution. The narrative reports discuss the type of incident, the time of the incident, the number of people who respond, the cost to the organization, and whether or not that incident was successfully or unsuccessfully resolved. There are roughly 10,000 reports. Which series of approaches is most likely to result in a product that would satisfy the customer's request?