8 items tagged “semanticweb”
2023
I expect GPT-4 will have a LOT of applications in web scraping
The increased 32,000 token limit will be large enough to send it the full DOM of most pages, serialized to HTML - then ask questions to extract data
Or... take a screenshot and use the GPT4 image input mode to ask questions about the visually rendered page instead!
Might need to dust off all of those old semantic web dreams, because the world's information is rapidly becoming fully machine readable
— Me
2010
Linked Data at the Guardian. The Guardian’s Open Platform API can now be queried by MusicBrainz ID and ISBN, opening up some extremely useful new types of query.
2009
4store Amazon Machine Image. Instructions for firing up an EC2 AMI running the recently released 4store high performance triple store and loading in 1.14 billion statements collected by crawling the semantic web.
2008
Learning to Fear the Semantic Web. Paul Ford raises the liability issue with regards to building sites around other people’s metadata, pointing out that OpenCalais is owned by Thomson Reuters who have a bad track record with regards to intellectual property lawsuits elsewhere in the organisation.
The only down side is everyone I’ve talked to at Freebase seems pretty solid on this being their proprietary secret sauce, because a good, fast scalable open source tuple store might actually jump start a real semantic (small-S) web after all these years.
2007
Giant Global Graph. Tim Berners-Lee points out that the Semantic Web is designed to solve problems such as portable social networks.
dbpedia.org. They scrape Wikipedia and extract useful information from it so you don’t have to.
Triplr. Ultra simple GET-based web service for converting RSS / Atom / RDF / Microformats+GRDDL to HTML / ntriples / RDF / RSS / JSON / Turtle. Small pieces, loosely joined.