Grounded QA with an explicit "unsure" fallback

The prompt

Answer the question based on the context below. Keep the answer short and concise. Respond "Unsure about answer" if not sure about the answer.

Context: Teplizumab traces its roots to a New Jersey drug company called Ortho Pharmaceutical. There, scientists generated an early version of the antibody, dubbed OKT3. Originally sourced from mice, the molecule was able to bind to the surface of T cells and limit their cell-killing potential. In 1986, it was approved to help prevent organ rejection after kidney transplants, making it the first therapeutic antibody allowed for human use.

Question: What was OKT3 originally sourced from?
Answer:

Expected result

"Mice" — a short, grounded answer pulled directly from the context, with an explicit fallback ("Unsure about answer") built in for questions the context doesn't actually cover.

Why it works

A closed-context QA template: pasting the source text directly into the prompt and adding an explicit uncertainty fallback reduces confident-sounding wrong answers, since the model is told exactly what it's allowed to answer from.