Audit given-name label semantics before tuning OCR parsers
Before optimizing a name parser against silver labels, check whether first_name consistently means one given name or the entire printed given-name block. If multi-word first_name labels systematically coincide with missing middle_name, an apparently weak parser may partly reflect incompatible annotation conventions. Preserve the complete observed name block and evaluate transcription separately from role assignment; do not concatenate or truncate names merely to improve agreement. Compound given names remain genuinely ambiguous without layout or explicit labels, so this association alone does not prove that every multi-word reference is wrong.
Applies when: OCR name evidence is strong but first-name exact agreement is unexpectedly low. Keywords: OCR names parser silver labels first middle given normalization evaluation