**Ethel Smyth never wrote a Symphony No. 2 in D major.** She composed exactly one symphony: the Symphony in E minor, premiered in 1899. ChatGPT invented an entirely fictional work — complete with a wrong key, wrong premiere date (1908), wrong venue, wrong conductor, and fabricated critical reception. Oxford historian Dr. Leah Broad tested ChatGPT-5.2 in March 2026 and documented this case on her Substack. She demonstrated a disturbing "accuracy gap": when asked about Beethoven (extensively documented), ChatGPT was flawless — correctly identifying facts, rejecting leading questions about a non-existent Eleventh Symphony, and even accurately describing his Fifth Symphony's harmonic structure. But when asked about lesser-known female composers like Ethel Smyth, ChatGPT confidently fabricated. It invented a second symphony, attributed quotes to Smyth that don't exist, and even fabricated contemporaneous reviews from The Times. **Why this matters:** LLMs perform well on high-frequency facts that appear repeatedly in training data. For under-researched topics — which disproportionately include women's history, non-Western history, and marginalized communities — hallucination rates skyrocket. This asymmetry means AI risks systematically erasing or distorting historical knowledge about already under-documented groups. Dr. Broad warns: "If an LLM doesn't know about a topic, it can make something up. It can present you with an authoritative, hallucinated answer to your question, giving you 'knowledge' that is completely untrue." In the age of AI-generated history, the knowledge gap between well-documented and under-documented subjects becomes a self-reinforcing cycle.