How can I use NER Model from Simple Transformers with phrases instead of words, and startchar_endchar (mapping to text) instead of sentence_id?

Question

My data is in BRAT annotation format and I would like to use NER_Model from SimpleTransformers to test performance on this data with a variety of models. Is it possible to reshape my data in a way that can utilize NER_Model? Any suggestions or logic is greatly appreciated. There are four possible Entities (Microorganism, Habitat, Geographical, Phenotype)

BRAT Annotation .a2 file example data:
T5 Habitat 256 267 respiratory
T6 Habitat 281 290 pediatric
T7 Habitat 339 372 children less than 2 years of age
T8 Habitat 418 488 children greater than 9 years of age who had lower respiratory illness