This particular situation is not in the training data, though I’m sure it will be soon to try to shore up claims of ‘reasoning’.

The goal of training data is not to collect and reproduce facts. It is to align the model with the statistical probability of producing the correct (expected) response for data outside of its knowledge domain. This is called generalization [1], and it has been explored in depth.

[1]: https://arxiv.org/abs/2312.17173