[[{"@type":["BlogPosting"],"@id":"https:\/\/www.schemaapp.com\/schema-markup\/measurable-impact-of-scaling-entity-linking-for-entity-disambiguation\/#BlogPosting","@context":{"@vocab":"http:\/\/schema.org\/","kg":"http:\/\/g.co\/kg"},"url":"https:\/\/www.schemaapp.com\/schema-markup\/measurable-impact-of-scaling-entity-linking-for-entity-disambiguation\/","publisher":[{"@id":"https:\/\/www.schemaapp.com\/#Organization"}],"audience":"https:\/\/schema.org\/PeopleAudience","inLanguage":[{"@type":"Language","@id":"https:\/\/www.schemaapp.com\/schema-markup\/measurable-impact-of-scaling-entity-linking-for-entity-disambiguation\/#BlogPosting_inLanguage_Language","name":"English"}],"mentions":[{"@id":"https:\/\/www.schemaapp.com\/entity#Thing19"},{"@id":"https:\/\/www.schemaapp.com\/entity#Thing13"},{"@id":"https:\/\/www.schemaapp.com\/#Organization"},{"@id":"https:\/\/www.schemaapp.com\/entity#Thing4"}],"dateModified":"2024-03-25T16:39:36+00:00","headline":"Measurable Impact of Scaling Entity Linking for Entity Disambiguation","datePublished":"2024-02-27T22:27:45+00:00","image":[{"@type":"ImageObject","@id":"https:\/\/www.schemaapp.com\/schema-markup\/measurable-impact-of-scaling-entity-linking-for-entity-disambiguation\/#BlogPosting_image_ImageObject","url":"https:\/\/www.schemaapp.com\/wp-content\/uploads\/2024\/02\/Impact-of-Scaling-Entity-Linking.png"}],"mainEntityOfPage":"https:\/\/www.schemaapp.com\/schema-markup\/measurable-impact-of-scaling-entity-linking-for-entity-disambiguation\/","name":"Measurable Impact of Scaling Entity Linking for Entity Disambiguation","articleBody":"In the past, we\u2019ve measured the value of Schema Markup purely through the lens of rich results.\nHowever, we\u2019ve seen a lot of changes in rich results and the overall search experience this past year. The uprising of generative AI-powered search engines, accompanied by the volatility in rich results, has prompted our team to dive deeper into the semantic value of Schema Markup and entity linking as it pertains to search today.\nIn this article, we will share the value of entity linking, the tools enabling you to do it at scale and the results we\u2019ve seen from implementing entity linking with our Enterprise clients.\nGrowing Importance of Entities in Search\nOver the past decade, search engines have shifted from lexical to semantic search to improve the accuracy and relevancy of their search results.\nAs a result, how we think about search engine optimization also has to change. We have to move away from adding keywords to a page and go towards identifying entities on a page to help search engines and machines understand and contextualize the content on our pages.\nEntities are a single, unique, well-defined, distinguishable thing or idea. An entity can be anything from a person to a place to a concept, and they possess defining characteristics or attributes (i.e. colour, price, name). But they need to be described in relation to other things to have meaning. For example, Schema App is an entity that can be described by its name, location, website URL, founders, employees and more.\nYour website content contains entities related to your organization, and you can help search engines identify the entities on your page using Schema Markup.\nWhen you implement Schema Markup on your page, you are identifying and describing the entities in your content, which helps search engines better understand your content.\nWhile having entities defined on your site is good, you can go one step further and improve your markup by doing entity linking to build a connected, robust content knowledge graph.\nA content knowledge graph is a collection of relationships between the entities defined on your website, defined using a standardized vocabulary like Schema.org. It enables search engines and other machines to gain new knowledge about your organization through inference.\nSign up for our free course to learn the fundamentals of content knowledge graphsEnroll now\nWhat is Entity Linking?\nEntity linking is the act of identifying entities mentioned in text, and linking them to corresponding entities that have been defined in a target knowledge base.\nIn the context of Schema Markup, entity linking is the act of linking the entities on your site to the corresponding known entities on external authoritative knowledge bases such as Wikipedia, Wikidata and Google\u2019s Knowledge Graph using Schema.org properties. Examples of connector properties include sameAs, mentions, areaServed, and more.\nExternal authoritative knowledge bases can differ by vertical or content type. For example, if you are in the medical or finance industry, there may be a governing body or glossary that best defines the entities within your content.\nEntity linking can help you define the terms and entities mentioned in your content more explicitly, thus enabling search engines to disambiguate the entity identified on your site with greater confidence and provide users with more accurate and relevant search results.\nFor example, if your page talks about \u2018London,\u2019 this can be confusing to search engines because there are several cities in the world named London. You can help search engines disambiguate which London you are referring to in your content by linking to the same known entity described on Wikipedia, Wikidata or Google\u2019s Knowledge Graph.\nSuppose we are talking about the city of London in Ontario, Canada. In that case, we can use the sameAs property to link the entity on your site to the known entity on Wikipedia, Wikidata and Google\u2019s Knowledge Graph. Doing this entity linking makes it explicit to search engines that the content on the page is about \u2018London, Ontario, Canada\u2019 and not \u2018London, England\u2019.\n \"mentions\": {\n \"@type\u201d: \"Place\",\n \"name\": \"London\",\n \"sameAs\": \"https:\/\/www.wikidata.org\/wiki\/Q92561\",\n \"sameAs\": \"https:\/\/en.wikipedia.org\/wiki\/London,_Ontario\",\n \"sameAs\": \"kg:\/m\/0b1t1\",\n}\n\nEntity linking is even more vital if your organization is in an industry where being specific is essential (such as defining a medical condition or a specific financial instrument like new construction financing).\nApproaches to Entity Linking\nYou could take two main approaches to entity linking: a general approach and a more strategic one.\nGeneral Approach to Entity Linking\nYou could take a general approach and identify any entity on your site, check if it is a known entity on an external authoritative knowledge base, and, if it is, link that entity to the known entities.\nFor example, if you are a technology company, your product pages might mention entities like SOC2, Solution, and the United States. Using the general entity linking approach, you can link these entities to the known entities on external authoritative knowledge bases.\nStrategic Approach to Entity Linking\nAlternatively, you can take a more strategic approach and identify a specific type of entity on your site (for example, locations mentioned on your site or a particular term mentioned on your site), check if it is a known entity on an external authoritative knowledge base, and if it is, link that entity to the known entities.\nFor example, you can use a place-based entity linking approach to explicitly identify the place entities mentioned on a page and link them to the known entities on Wikipedia, Wikidata and Google\u2019s Knowledge Graph.\nIf your website has different location-based landing pages for your offering, you can implement place-based entity linking in your Schema Markup. Doing so would help search engines understand the locations that your organization is servicing and enable your page to perform better on \u2018near me\u2019 and other location-based searches.\nThe entities you target with entity linking should be purposeful. Instead of linking all the entities on a page with corresponding known entities, you should focus on linking the most essential ones for clarity.\nHow we do Entity Linking at Schema App\nAt Schema App, we believe that entity linking is crucial to developing a robust content knowledge graph. It can add value to your SEO efforts and prepare you to get further insights from your content. So, how can you do entity linking within your markup?\nYou can manually link the entities on your page to the known entities on external authoritative knowledge bases. However, this solution is not dynamic nor scalable, so keeping the data updated and accurate can be resource-intensive and time-consuming.\nThe Schema App team developed the Omni LER feature to apply entity linking in a scalable, dynamic manner to solve the scale and accuracy of entity linking.\nOmni Linked Entity Recognition (LER) is the automated process of identifying entities mentioned in texts and linking them to the corresponding entities on authoritative knowledge bases (like Wikipedia, Wikidata and the Google Knowledge Graph).\nToday, Schema App\u2019s Omni LER feature uses natural language processing to identify entities within a block of text automatically and embed them within the Schema Markup based on the Schema Markup configuration in the Schema App Highlighter.\nIn the future, we\u2019ll introduce a controlled vocabulary feature to help our customers identify which entities they want to map to for entity linking. This evolution will give organizations even more control over the topics and entities they want to be known for and how they want to define those entities.\nEntity Linking Experiments and Results\nThe impact of entity linking on SEO has yet to be explored widely. This prompted our team to experiment with entity linking to see if it has any measurable impact on SEO metrics.\nUsing our Omni LER feature, we implemented entity linking on over 60 enterprise customer accounts in healthcare, finance, B2B technology and other industries.\nWe ran general and place-based entity linking experiments on a variety of pages (i.e. blogs, location pages, medical pages, etc.) over three months and measured the impact on search performance. Here\u2019s what we saw as the results.\nGeneral Entity Linking Experiment\nWe took the general entity linking approach on pages with long-form content, such as blogs. The Omni LER feature within the Schema App Highlighter identified the named entities in the text and embedded the known entities in the markup using the mentions and sameAs properties within the schema markup for the page.\nFor example, one customer had a blog article about rashes caused by amoxicillin. We used the \u201cmentions\u201d property to identify \u2018Amoxicillin\u2019 as an entity on the blog post and further clarified the entity by nesting the equivalent entities defined on Wikipedia and Google\u2019s Knowledge Graph for Amoxicillin.\n<img fetchpriority=\"high\" decoding=\"async\" class=\"alignnone wp-image-14750\" src=\"https:\/\/ezk8caoodod.exactdn.com\/wp-content\/uploads\/2024\/02\/Screenshot-2024-02-26-at-11.13.37\u202fAM.png?strip=all&lossy=1&resize=856%2C215&ssl=1\" alt=\"Screenshot of external entity linking for the entity Amoxicillin\" width=\"856\" height=\"215\" srcset=\"https:\/\/ezk8caoodod.exactdn.com\/wp-content\/uploads\/2024\/02\/Screenshot-2024-02-26-at-11.13.37\u202fAM-80x21.png?strip=all&amp;lossy=1&amp;ssl=1 80w, https:\/\/ezk8caoodod.exactdn.com\/wp-content\/uploads\/2024\/02\/Screenshot-2024-02-26-at-11.13.37\u202fAM-100x26.png?strip=all&amp;lossy=1&amp;ssl=1 100w, https:\/\/ezk8caoodod.exactdn.com\/wp-content\/uploads\/2024\/02\/Screenshot-2024-02-26-at-11.13.37\u202fAM-30x8.png?strip=all&amp;lossy=1&amp;ssl=1 30w, https:\/\/ezk8caoodod.exactdn.com\/wp-content\/uploads\/2024\/02\/Screenshot-2024-02-26-at-11.13.37\u202fAM-50x13.png?strip=all&amp;lossy=1&amp;ssl=1 50w, https:\/\/ezk8caoodod.exactdn.com\/wp-content\/uploads\/2024\/02\/Screenshot-2024-02-26-at-11.13.37\u202fAM-114x30.png?strip=all&amp;lossy=1&amp;ssl=1 114w, https:\/\/ezk8caoodod.exactdn.com\/wp-content\/uploads\/2024\/02\/Screenshot-2024-02-26-at-11.13.37\u202fAM.png?strip=all&amp;lossy=1&amp;zoom=0.2&amp;resize=856%2C215&amp;ssl=1 171w, https:\/\/ezk8caoodod.exactdn.com\/wp-content\/uploads\/2024\/02\/Screenshot-2024-02-26-at-11.13.37\u202fAM.png?strip=all&amp;lossy=1&amp;zoom=0.4&amp;resize=856%2C215&amp;ssl=1 342w, https:\/\/ezk8caoodod.exactdn.com\/wp-content\/uploads\/2024\/02\/Screenshot-2024-02-26-at-11.13.37\u202fAM.png?strip=all&amp;lossy=1&amp;zoom=0.6&amp;resize=856%2C215&amp;ssl=1 513w, https:\/\/ezk8caoodod.exactdn.com\/wp-content\/uploads\/2024\/02\/Screenshot-2024-02-26-at-11.13.37\u202fAM.png?strip=all&amp;lossy=1&amp;zoom=0.8&amp;resize=856%2C215&amp;ssl=1 684w, https:\/\/ezk8caoodod.exactdn.com\/wp-content\/uploads\/2024\/02\/Screenshot-2024-02-26-at-11.13.37\u202fAM.png?strip=all&amp;lossy=1&amp;zoom=1&amp;resize=856%2C215&amp;ssl=1 856w\" sizes=\"(max-width: 856px) 100vw, 856px\" \/>\nThe Omni LER feature also identified other entities on the page, such as \u2018Benadryl\u2019, \u2018Keflex\u2019, \u2018Mononucleosis\u2019 \u2018National Institutes of Health\u2019, and linked these entities to the known entities on Wikipedia, Wikidata and Google\u2019s Knowledge graph under the relevant schema markup property.\nAfter implementing entity linking on that blog article, the customer saw a 336% increase in click-through rate for the query \u2018Amoxicillin rash\u2019 and a 390% increase in click-through rate for the query \u2018Rash from amoxicillin\u2019. The number of queries for that blog also increased by 86.75%.\nAcross our customer set, we saw an overall trend where the clicks and click-through rates increased for relevant keywords while the number of irrelevant keywords dropped for each page.\nPlaced-based Entity Linking Experiment\nIn a second experiment, we took the placed-based entity linking approach on location-based landing pages. This customer had a set of location-based landing pages to cater to their audiences in different states across the US.\nWe implemented placed-based entity linking on 11 test pages and kept 4 control pages to compare the results.\nOn the test pages, we added spatialCoverage and audience property in the markup to identify the state this page pertained to (in this example, it was for the state of California) and then further clarified which \u2018California\u2019 we were referring to by nesting the equivalent entities defined on Wikipedia, Wikidata and Google\u2019s knowledge graph using the sameAs property.\n<img decoding=\"async\" class=\"alignnone size-full wp-image-14752\" src=\"https:\/\/www.schemaapp.com\/wp-content\/uploads\/2024\/02\/Example-of-markup-with-entity-linking-scaled.webp\" alt=\"Example of placed-based external entity linking\" width=\"699\" height=\"588\" srcset=\"https:\/\/www.schemaapp.com\/wp-content\/uploads\/2024\/02\/Example-of-markup-with-entity-linking-scaled.webp 699w, https:\/\/www.schemaapp.com\/wp-content\/uploads\/2024\/02\/Example-of-markup-with-entity-linking-300x252.webp 300w, https:\/\/www.schemaapp.com\/wp-content\/uploads\/2024\/02\/Example-of-markup-with-entity-linking-1024x861.webp 1024w, https:\/\/www.schemaapp.com\/wp-content\/uploads\/2024\/02\/Example-of-markup-with-entity-linking-600x504.webp 600w, https:\/\/www.schemaapp.com\/wp-content\/uploads\/2024\/02\/Example-of-markup-with-entity-linking-768x646.webp 768w, https:\/\/www.schemaapp.com\/wp-content\/uploads\/2024\/02\/Example-of-markup-with-entity-linking-714x600.webp 714w, https:\/\/www.schemaapp.com\/wp-content\/uploads\/2024\/02\/Example-of-markup-with-entity-linking-80x67.webp 80w, https:\/\/www.schemaapp.com\/wp-content\/uploads\/2024\/02\/Example-of-markup-with-entity-linking-276x232.webp 276w, https:\/\/www.schemaapp.com\/wp-content\/uploads\/2024\/02\/Example-of-markup-with-entity-linking-200x168.webp 200w, https:\/\/www.schemaapp.com\/wp-content\/uploads\/2024\/02\/Example-of-markup-with-entity-linking-71x60.webp 71w, https:\/\/www.schemaapp.com\/wp-content\/uploads\/2024\/02\/Example-of-markup-with-entity-linking-119x100.webp 119w, https:\/\/www.schemaapp.com\/wp-content\/uploads\/2024\/02\/Example-of-markup-with-entity-linking-140x118.webp 140w, https:\/\/www.schemaapp.com\/wp-content\/uploads\/2024\/02\/Example-of-markup-with-entity-linking-400x336.webp 400w, https:\/\/www.schemaapp.com\/wp-content\/uploads\/2024\/02\/Example-of-markup-with-entity-linking-220x185.webp 220w, https:\/\/www.schemaapp.com\/wp-content\/uploads\/2024\/02\/Example-of-markup-with-entity-linking-100x84.webp 100w, https:\/\/www.schemaapp.com\/wp-content\/uploads\/2024\/02\/Example-of-markup-with-entity-linking-450x378.webp 450w, https:\/\/www.schemaapp.com\/wp-content\/uploads\/2024\/02\/Example-of-markup-with-entity-linking-1300x1093.webp 1300w, https:\/\/www.schemaapp.com\/wp-content\/uploads\/2024\/02\/Example-of-markup-with-entity-linking-150x126.webp 150w, https:\/\/www.schemaapp.com\/wp-content\/uploads\/2024\/02\/Example-of-markup-with-entity-linking-30x25.webp 30w, https:\/\/www.schemaapp.com\/wp-content\/uploads\/2024\/02\/Example-of-markup-with-entity-linking-50x42.webp 50w, https:\/\/www.schemaapp.com\/wp-content\/uploads\/2024\/02\/Example-of-markup-with-entity-linking-36x30.webp 36w, https:\/\/www.schemaapp.com\/wp-content\/uploads\/2024\/02\/Example-of-markup-with-entity-linking-42x35.webp 42w\" sizes=\"(max-width: 699px) 100vw, 699px\" \/>\nAfter running the experiment for 85 days, the test sites saw an increase in the number of queries containing the state name and \u2018near me\u2019, leading to a 46% increase in impressions and a 42% increase in clicks for non-branded queries.\nBy clarifying the locations serviced on the site, this customer\u2019s pages showed up for more location-based queries.\nDo Entity Linking at Scale\nBased on the early results we\u2019ve seen, entity linking can help search engines disambiguate the entities mentioned on your site and help your pages show up for more relevant search queries, increasing the clicks and click-through rate to the pages. It is a great way to stand out in search and drive more qualified traffic to your site.\nEntity linking can also help your organization build a more descriptive content knowledge graph. You can learn more about content knowledge graphs through our free \u2018Content Knowledge Graph Fundamentals\u2019 course.\nIf you want to implement entity linking at scale or build a content knowledge graph for your site, contact us.","description":"Learn about the value of entity linking using Schema Markup and the results we\u2019ve seen from implementing entity linking with our customers."},{"@context":"http:\/\/schema.org","@type":"Organization","address":{"@type":"PostalAddress","streetAddress":"201 - 412 Laird Road","postalCode":"N1G 3X7","addressRegion":"Ontario","addressLocality":"Guelph","addressCountry":"https:\/\/www.schemaapp.com\/#Country","name":"Schema App Address","@id":"https:\/\/www.schemaapp.com\/#PostalAddress"},"logo":{"@type":"ImageObject","width":"290","height":"93","url":"https:\/\/ezk8caoodod.exactdn.com\/wp-content\/uploads\/2020\/07\/SA_Logo_Main_Orange_w300-1.png?strip=all&lossy=1&ssl=1","@id":"https:\/\/ezk8caoodod.exactdn.com\/wp-content\/uploads\/2020\/07\/SA_Logo_Main_Orange_w300-1.png?strip=all&lossy=1&ssl=1"},"potentialAction":{"@type":"ScheduleAction","name":"Schedule a Demo","url":"https:\/\/www.schemaapp.com\/book-a-demo\/","@id":"https:\/\/www.schemaapp.com\/#ScheduleAction"},"image":{"@type":"ImageObject","width":"1350","height":"650","url":"https:\/\/ezk8caoodod.exactdn.com\/wp-content\/uploads\/2021\/04\/Schema-App-Featured-Image.png?strip=all&lossy=1&ssl=1","@id":"https:\/\/ezk8caoodod.exactdn.com\/wp-content\/uploads\/2021\/04\/Schema-App-Featured-Image.png?strip=all&lossy=1&ssl=1"},"description":"Schema App is an end-to-end Schema Markup solution that helps enterprise SEO teams develop a knowledge graph and drive search performance.","knowsAbout":["http:\/\/www.wikidata.org\/entity\/Q1891170","https:\/\/www.wikidata.org\/wiki\/Q6108942","https:\/\/www.wikidata.org\/wiki\/Q26813700","https:\/\/www.wikidata.org\/wiki\/Q180711","http:\/\/www.wikidata.org\/entity\/Q33002955"],"keywords":["Structured Data","Knowledge Graph","Rich Results","Semantic Search","Search Engine Optimization","Schema Markup","Semantic Technology"],"location":"http:\/\/www.wikidata.org\/entity\/Q504114","sameAs":["https:\/\/www.instagram.com\/lifeatschemaapp\/","https:\/\/www.linkedin.com\/company\/2480720\/","https:\/\/twitter.com\/schemaapptool","https:\/\/www.youtube.com\/channel\/UCqVBXnwZ3YNf2BVP1jXcp6Q"],"legalName":"Hunch Manifest Inc","name":"Schema App","telephone":"+18554448624","url":"https:\/\/www.schemaapp.com\/","email":"support@schemaapp.com","knowsLanguage":"http:\/\/www.wikidata.org\/entity\/Q1860","areaServed":"http:\/\/www.wikidata.org\/entity\/Q13780930","@id":"https:\/\/www.schemaapp.com\/#Organization"},{"@context":"http:\/\/schema.org","@type":"Thing","sameAs":["http:\/\/www.wikidata.org\/entity\/Q180711","kg:\/m\/019qb_","https:\/\/en.wikipedia.org\/wiki\/Search_engine_optimization"],"name":"SEO","alternateName":"search engine optimization","description":"practice and strategies of increasing online visibility in search engine results pages","@id":"https:\/\/www.schemaapp.com\/entity#Thing19"},{"@context":"http:\/\/schema.org","@type":"Thing","name":"Knowledge Graph","sameAs":["https:\/\/en.wikipedia.org\/wiki\/Knowledge_graph","http:\/\/www.wikidata.org\/entity\/Q33002955","kg:\/g\/11jtynfm6d"],"description":"information repository structured as a graph","@id":"https:\/\/www.schemaapp.com\/entity#Thing13"},{"@context":"http:\/\/schema.org","@type":"Thing","sameAs":["kg:\/m\/0rysr6q","https:\/\/www.wikidata.org\/wiki\/Q17012245"],"description":"the task of assigning a unique identity to entities mentioned in text","name":"Entity Linking","@id":"https:\/\/www.schemaapp.com\/entity#Thing4"}],{"@context":"https:\/\/schema.org\/","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Schema Markup","item":"https:\/\/www.schemaapp.com\/schema-markup\/#breadcrumbitem"},{"@type":"ListItem","position":2,"name":"Measurable Impact of Scaling Entity Linking for Entity Disambiguation","item":"https:\/\/www.schemaapp.com\/schema-markup\/measurable-impact-of-scaling-entity-linking-for-entity-disambiguation\/#breadcrumbitem"}]}]