The basic conclusion of Mann et al. (1998, 1999) was that the late 20th century warmth in the Northern Hemisphere was unprecedented during at least the last 1,000 years. This conclusion has subsequently been supported by an array of evidence...
What's more interesting to me, however, is the additional claim, which many climate scientists have made, to the effect that any methodological short-comings in Mann's work are irrelevant, because his main findings have been replicated by alternative methods.
Which brings us to the graph top-left. It provides 500 years worth of average temperatures in the Ottawa, Ontario region and has been produced using one of these alternative methods. Specifically, it has been produced by dropping thermometers down pre-dug boreholes and recording the temperature change that occurs as this measuring device plunges deeper into the Earth. How the results are calculated from data-points gathered in this way, and some of the drawbacks to the method, can be found in this terrific (and only somewhat technical) post at Open Mind.
The original data can be found here.
Note the important thing: the graph pretty much replicates Mann's result.