This reminds me of an article I read about IBM's Watson. As a demo in front of a lot of people, a researcher was going through a stack of journals and feeding in data about anthrax. Most of the data was about animals, but the researcher was asking Watson to extrapolate possible effects on people. Watson responded "I assume by people you mean humans, and not People magazine."

Edit: found the link (PDF) http://www.cs.mtu.edu/~nilufer/classes/cs5811/2003-fall/hilt... Here's the actual quote:

  “Do you mean Anthrax (the heavy-metal band),
  anthrax (the bacterium) or anthrax (the disease)?”

  “The bacterium,” was the typed answer, followed by 
  the instruction, “Comment on its toxicity to people.”

  “I assume you mean people (homo sapiens),” the
  system responded, reasoning, as it informed its
  programmer, that asking about People magazine
  “would not make sense.”

Late edit: funny that I remembered this being Watson when it's actually Cyc, a longtime rival of the Watson project.

Just make the link to the disambiguation page, if there is one? Otherwise, make it a special link that doesn't go anywhere directly, but uses some javascript/CSS to raise a dialog when clicked, that gives you the different choices?

Auto-generate disambiguation pages?

When a search term matches a tag, and none of the tagged pages have a clear "majority probability" of being correct, it would display a list of all pages with the tag, in order of popularity.

I don't think it would be a good idea if wikipedia required that you to run Javascript to navigate the site, and it would make for pretty bad SEO.

Wikipedia doesn't need to care to much about SEO.

> Just make the link to the disambiguation page, if there is one? Otherwise, make it a special link that doesn't go anywhere directly, but uses some javascript/CSS to raise a dialog when clicked, that gives you the different choices?

Both of these things would be amazingly annoying to the majority of Wikipedia users.

I'm only talking about auto-generated links that can't be clearly disambiguated by the system. At worst, the experience wouldn't be any worse than it is today.

> I'm only talking about auto-generated links that can't be clearly disambiguated by the system.

But they could be disambiguated by humans, which is my point. Humans understand context.

Sure, and when humans create links, they should continue to create them just like they do not. I'm picturing an "auto linkifier" that creates links that no human has gotten around to creating yet.

Whether or not something like that would be a net win for Wikipedia is up for debate I guess. That said, I think they already do have a bot that can do at least a limited amount of auto-linkification, but I can't swear to it.

I guess an added bonus of what you're suggesting is that the correct link could be crowdsourced; if the system kept track of which of the options users clicked on, it could figure out pretty quickly which one is correct.

Exactly this.

It would take some AI to work it out, unless using the context around the link. "Sun" could refer to many things, its not really possible for wikipedia to know which one you're on about. So links are still done manually.