Nice answer, but it actually supports the point being made here. NLP is an attempt to see how far we can go in processing natural language, without doing this sort of translation, and without structured knowledge bases. As (I'm pretty sure) Wolfram Alpha contains a structured knowledge base and draws on it for this sort of question (though not without help in this case), its abilities are orthogonal to the issues addressed in the article.

A quibble is that when I see kg, mass, I expect that it should be measured the same whether on Earth or on the moon. The answer should be in Newtons.

Our query to Wolfram Alpha should thus be:

(mass of elephant)/2 * moon gravity

Good effort! But gram is not a unit of weight.