http://simonwillison.net/2023-03-16T01:09:52+00:00Simon Willison2023-03-16T01:09:52+00:002023-03-16T01:09:52+00:00https://simonwillison.net/2023/Mar/16/gpt4-scraping/

<blockquote cite="https://fedi.simonwillison.net/@simon/110030289294541249"><p>I expect GPT-4 will have a LOT of applications in web scraping</p> <p>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</p> <p>Or... take a screenshot and use the GPT4 image input mode to ask questions about the visually rendered page instead!</p> <p>Might need to dust off all of those old semantic web dreams, because the world's information is rapidly becoming fully machine readable</p></blockquote> <p class="cite">&mdash; <a href="https://fedi.simonwillison.net/@simon/110030289294541249">Me</a></p> <p>Tags: <a href="https://simonwillison.net/tags/scraping">scraping</a>, <a href="https://simonwillison.net/tags/semantic-web">semantic-web</a>, <a href="https://simonwillison.net/tags/gpt-4">gpt-4</a>, <a href="https://simonwillison.net/tags/llms">llms</a>, <a href="https://simonwillison.net/tags/gpt">gpt</a></p>

2010-10-19T19:11:00+00:002010-10-19T19:11:00+00:00https://simonwillison.net/2010/Oct/19/linked/

<p><strong><a href="http://www.guardian.co.uk/open-platform/blog/linked-data-open-platform">Linked Data at the Guardian</a></strong></p> The Guardian’s Open Platform API can now be queried by MusicBrainz ID and ISBN, opening up some extremely useful new types of query. <p>Tags: <a href="https://simonwillison.net/tags/guardian">guardian</a>, <a href="https://simonwillison.net/tags/openplatform">openplatform</a>, <a href="https://simonwillison.net/tags/semantic-web">semantic-web</a>, <a href="https://simonwillison.net/tags/recovered">recovered</a></p>

2009-11-01T12:12:24+00:002009-11-01T12:12:24+00:00https://simonwillison.net/2009/Nov/1/4store/

<p><strong><a href="http://thinklinks.wordpress.com/2009/10/27/4store-amazon-machine-image-and-billion-triple-challenge-data-set/">4store Amazon Machine Image</a></strong></p> 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. <p>Tags: <a href="https://simonwillison.net/tags/4store">4store</a>, <a href="https://simonwillison.net/tags/ami">ami</a>, <a href="https://simonwillison.net/tags/ec2">ec2</a>, <a href="https://simonwillison.net/tags/semantic-web">semantic-web</a>, <a href="https://simonwillison.net/tags/semweb">semweb</a>, <a href="https://simonwillison.net/tags/triplestore">triplestore</a></p>

2008-10-23T16:14:03+00:002008-10-23T16:14:03+00:00https://simonwillison.net/2008/Oct/23/learning/

<p><strong><a href="http://ftrain.com/a-semantic-web-fear.html">Learning to Fear the Semantic Web</a></strong></p> 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. <p>Tags: <a href="https://simonwillison.net/tags/intellectualproperty">intellectualproperty</a>, <a href="https://simonwillison.net/tags/opencalais">opencalais</a>, <a href="https://simonwillison.net/tags/paul-ford">paul-ford</a>, <a href="https://simonwillison.net/tags/semantic-web">semantic-web</a>, <a href="https://simonwillison.net/tags/thomson-reuters">thomson-reuters</a></p>

2008-09-29T15:29:34+00:002008-09-29T15:29:34+00:00https://simonwillison.net/2008/Sep/29/secretsauce/

<blockquote cite="http://laughingmeme.org/2008/09/29/on-the-freebase-custom-tuple-store-graphd/"><p>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.</p></blockquote> <p class="cite">&mdash; <a href="http://laughingmeme.org/2008/09/29/on-the-freebase-custom-tuple-store-graphd/">Kellan Elliott-McCrea</a></p> <p>Tags: <a href="https://simonwillison.net/tags/freebase">freebase</a>, <a href="https://simonwillison.net/tags/graphd">graphd</a>, <a href="https://simonwillison.net/tags/kellan-elliott-mccrea">kellan-elliott-mccrea</a>, <a href="https://simonwillison.net/tags/open-source">open-source</a>, <a href="https://simonwillison.net/tags/proprietary">proprietary</a>, <a href="https://simonwillison.net/tags/semantic-web">semantic-web</a></p>

2007-11-22T00:30:23+00:002007-11-22T00:30:23+00:00https://simonwillison.net/2007/Nov/22/timbl/

<p><strong><a href="http://dig.csail.mit.edu/breadcrumbs/node/215">Giant Global Graph</a></strong></p> Tim Berners-Lee points out that the Semantic Web is designed to solve problems such as portable social networks. <p>Tags: <a href="https://simonwillison.net/tags/openid">openid</a>, <a href="https://simonwillison.net/tags/portablesocialnetworks">portablesocialnetworks</a>, <a href="https://simonwillison.net/tags/semantic-web">semantic-web</a>, <a href="https://simonwillison.net/tags/social-graph">social-graph</a>, <a href="https://simonwillison.net/tags/tim-berners-lee">tim-berners-lee</a></p>

2007-08-07T15:24:20+00:002007-08-07T15:24:20+00:00https://simonwillison.net/2007/Aug/7/dbpediaorg/

<p><strong><a href="http://dbpedia.org/docs/">dbpedia.org</a></strong></p> They scrape Wikipedia and extract useful information from it so you don’t have to. <p>Tags: <a href="https://simonwillison.net/tags/dbpedia">dbpedia</a>, <a href="https://simonwillison.net/tags/semantic-web">semantic-web</a>, <a href="https://simonwillison.net/tags/wikipedia">wikipedia</a></p>

2007-03-30T15:30:15+00:002007-03-30T15:30:15+00:00https://simonwillison.net/2007/Mar/30/triplr/

<p><strong><a href="http://triplr.org/">Triplr</a></strong></p> Ultra simple GET-based web service for converting RSS / Atom / RDF / Microformats+GRDDL to HTML / ntriples / RDF / RSS / JSON / Turtle. Small pieces, loosely joined. <p>Tags: <a href="https://simonwillison.net/tags/atom">atom</a>, <a href="https://simonwillison.net/tags/grddl">grddl</a>, <a href="https://simonwillison.net/tags/html">html</a>, <a href="https://simonwillison.net/tags/json">json</a>, <a href="https://simonwillison.net/tags/microformats">microformats</a>, <a href="https://simonwillison.net/tags/ntriples">ntriples</a>, <a href="https://simonwillison.net/tags/rdf">rdf</a>, <a href="https://simonwillison.net/tags/rss">rss</a>, <a href="https://simonwillison.net/tags/semantic-web">semantic-web</a>, <a href="https://simonwillison.net/tags/triplr">triplr</a>, <a href="https://simonwillison.net/tags/turtle">turtle</a></p>

2005-10-25T17:51:11+00:002005-10-25T17:51:11+00:00https://simonwillison.net/2005/Oct/25/google/

<p><strong><a href="http://google-blog.dirson.com/post.new/0292/">Google Base, the spirit of our times</a></strong></p> Are Google about to kick-start a centralised imitation of the semantic web? <p>Tags: <a href="https://simonwillison.net/tags/semantic-web">semantic-web</a></p>

2003-12-02T04:06:20+00:002003-12-02T04:06:20+00:00https://simonwillison.net/2003/Dec/2/new/

<p><strong><a href="http://www.ftrain.com/AWebSiteForHarpers.html">A New Website for Harper&#x27;s Magazine</a></strong></p> Paul Ford’s semantic web publishing system gets a commercial outing <p>Tags: <a href="https://simonwillison.net/tags/paul-ford">paul-ford</a>, <a href="https://simonwillison.net/tags/semantic-web">semantic-web</a></p>

2003-06-23T18:08:20+00:002003-06-23T18:08:20+00:00https://simonwillison.net/2003/Jun/23/sportingGentleman/

<p>If you're still wondering what <acronym title="Resource Description Framework">RDF</acronym> is actually <em>for</em>, Ben Hammersley's <a href="http://www.benhammersley.com/reboot/">Sporting Gentleman's Guide to the Semantic Web</a> includes a perfect example of triples (even if it get's a bit less obvious after that).</p> <p>Tags: <a href="https://simonwillison.net/tags/semantic-web">semantic-web</a></p>

2002-11-03T13:34:19+00:002002-11-03T13:34:19+00:00https://simonwillison.net/2002/Nov/3/theSemanticWebExplained/

<p><a href="http://www.decafbad.com/news_archives/000315.phtml">What the frell is the Semantic Web?</a> (<a href="http://tidakada.com/archives/p/1939/more/1/c/1" title="the semantic web for dummies">via tidakada</a>):</p> <blockquote cite="http://www.decafbad.com/news_archives/000315.phtml"> <p>Imagine a document containing exactly all of the same info your weblog page presents - only the data is completely, easily accessible to a robot in a universal, easily handled format.</p> <p>Furthermore, imagine that the schema describing the data to be found on your page is in that same format. And then, imagine that the document describing the construction of schema is in that same format. And then imagine that the decomposition continues, all of the way down to base data types and relationships. Eventually, the whole thing rests on the back of a turtle - er I mean a sort of universal client.</p> </blockquote> <p>This is the best introduction to the semantic web I've seen. I thought I'd "got it" after reading <a href="http://www.ftrain.com/google_takes_all.html">August 2009: How Google beat Amazon and Ebay to the Semantic Web</a> but the idea of decomposing the relationships down to something universally understandable only just clicked (also thanks to a course on Logic and Semantics I am taking at University at the moment). I think I get RDF tuples now as well (there's a good introduction in <a href="http://www.dbis.informatik.uni-frankfurt.de/~tolle/RDF/RDFIntro.html" title="Introduction to RDF">this document</a>).</p> <p>Tags: <a href="https://simonwillison.net/tags/semantic-web">semantic-web</a></p>

2002-08-31T14:41:45+00:002002-08-31T14:41:45+00:00https://simonwillison.net/2002/Aug/31/semanticWeb123/

<p><a href="http://www.disobey.com/detergent/2002/sw123/">The Semantic Web: 1-2-3</a> is an invaluable collection of links to semantic web resources, compiled by Morbus Iff. Morbis is the author of <a href="http://www.disobey.com/amphetadesk/">Amphetadesk</a>, an excellent news aggregator which was <a href="http://www.guardian.co.uk/online/story/0,3605,781838,00.html" title="Working the web: Newsreaders">reviewed favourably</a> by Ben Hammersley in the Gaurdian just the other day.</p> <p>Tags: <a href="https://simonwillison.net/tags/semantic-web">semantic-web</a></p>

2002-07-26T13:34:33+00:002002-07-26T13:34:33+00:00https://simonwillison.net/2002/Jul/26/googleAndTheSemanticWeb/

<p>I've long been wondering what kind of research Google are doing with respect to the Semantic Web. <a href="http://www.ftrain.com/google_takes_all.html">August 2009: How Google beat Amazon and Ebay to the Semantic Web</a> (via <a href="http://www.dellah.com/orient/2002/07/26/googlebots_go_botty.shtml">From the Orient</a>) is a superbly written essay which explains the concepts behind the Semantic Web through a "history" of how Google has become the world's largest marketplace by the year 2009. Stuart has written <a href="http://www.kryogenix.org/writings/tech/semanticweb.cas" title="Semantic web">his own essay</a> discussing some of the issues raised by the piece, such as security and classification problems.</p> <p>Tags: <a href="https://simonwillison.net/tags/semantic-web">semantic-web</a></p>

2002-07-10T15:49:55+00:002002-07-10T15:49:55+00:00https://simonwillison.net/2002/Jul/10/semanticWebExplained/

<p>I just found a nice, clear and above all short explanation of the Semantic Web at The <acronym title="World Wide Web Consortium">W3C</acronym>'s <a href="http://www.w3.org/TandS/#Semantic">Technology &amp; Society Domain</a> page:</p> <blockquote cite="http://www.w3.org/TandS/#Semantic"><p>The Semantic Web seeks to augment the current Web of <em>linked documents</em> with a Web of <em>linked data</em>. Today, Web users follow links from document to document in a largely manual process. Tomorrow, semantically-enabled links will enable both human users, and human users assisted by computers, to navigated these links and find the information they are looking for. [...] To reach its full potential, the Web must becomes a place where data can be shared and processed by automated tools as well as by people.</p></blockquote> <p>Tags: <a href="https://simonwillison.net/tags/semantic-web">semantic-web</a></p>

2002-06-22T16:30:50+00:002002-06-22T16:30:50+00:00https://simonwillison.net/2002/Jun/22/semanticWebsite/

XML.com: <a href="http://www.xml.com/pub/a/2001/05/02/semanticwebsite.html">Building a Semantic Web Site</a>. A top down guide to RSS and associated metadata concepts, including Dublin Core and Topic Maps. <p>Tags: <a href="https://simonwillison.net/tags/semantic-web">semantic-web</a></p>