This article introduces Critical Generative Interpretation, a method that supports humanist inquiry by making AI-generated insights traceable and grounded in textual evidence. By linking large language model (LLM) outputs to structured knowledge graphs derived from source texts, the method enables scholars to critically assess where generated interpretations come from and how they relate to the original material. This methodology supports humanist inquiry through close reading. Through a case study of Harold and the Purple Crayon, the article shows how this approach fosters interpretive engagement and makes AI a method for humanistic knowledge production.