Since you mention insurance documents, could you speak to how well this would extract data from a policy document like https://ahca.myflorida.com/medicaid/Prescribed_Drug/drug_cri... ?
The unstoppable administrative engine that is the American Healthcare system produces hundreds of thousands of continuously updated documents like this with no standardized format/structure.
Manually extracting/normalizing this data into a querable format is an industry all its own.