@prefix this: . @prefix sub: . @prefix schema: . @prefix np: . @prefix dct: . @prefix pav: . @prefix nt: . @prefix npx: . @prefix xsd: . @prefix rdfs: . @prefix prov: . @prefix wd: . @prefix foaf: . sub:Head { this: a np:Nanopublication; np:hasAssertion sub:assertion; np:hasProvenance sub:provenance; np:hasPublicationInfo sub:pubinfo . } sub:assertion { sub:llm-semantic-classification-or-both-designing-the-right a wd:Q604733; dct:description "

Organizations are increasingly evaluating large language models (LLMs) for content classification and tagging. While LLMs offer flexibility and can accelerate semantic model development, they also introduce considerations around consistency, explainability, governance, and cost.

This session compares LLM-driven classification, semantic classification, and hybrid approaches that combine the strengths of both. Through practical demonstrations and real-world examples, attendees will see how AI-assisted modeling can accelerate semantic model creation, while semantic classification delivers consistent, repeatable tagging across large volumes of enterprise content.

There will also be an examination of an often-overlooked architectural consideration: cost predictability. As document volumes grow, content is reprocessed to meet new business requirements, and AI licensing models evolve, the cost of token-based classification can become increasingly difficult to forecast.

"; dct:isPartOf ; pav:authoredBy sub:lance-thieshen; rdfs:label "LLM, Semantic Classification, or Both? Designing the Right Approach for Enterprise Data"; rdfs:seeAlso ; wd:P823 sub:lance-thieshen; schema:endDate "2026-10-01T10:40:00-04:00"^^xsd:dateTime; schema:location "New York Hilton Midtown Hotel"; schema:startDate "2026-10-01T10:10:00-04:00"^^xsd:dateTime . } sub:provenance { sub:assertion prov:wasAttributedTo ; prov:wasDerivedFrom . } sub:pubinfo { foaf:name "Ashley Caselli" . this: dct:created "2026-09-16T10:39:16Z"^^xsd:dateTime; dct:creator ; dct:license ; npx:introduces sub:llm-semantic-classification-or-both-designing-the-right; rdfs:label "Presentation: LLM, Semantic Classification, or Both? Designing the Right Approach for Enterprise Data"; nt:wasCreatedFromProvenanceTemplate ; nt:wasCreatedFromPubinfoTemplate , , , ; nt:wasCreatedFromTemplate . sub:lance-thieshen foaf:name "Lance Thieshen" . sub:sig npx:hasAlgorithm "RSA"; npx:hasPublicKey "MIIBIjANBgkqhkiG9w0BAQEFAAOCAQ8AMIIBCgKCAQEA+i9DV8ynzO944pYkYsDwtlqJHuk+b7FQt6Bb4TIQSDX3jGUURn6WpaNwESHmgMLWSydaH5XlabMzuqpPL4iyB+IAzvwIxdJBLhe39EQMu2j+FZ/5d/xu/gO3nZw2KoEvJ7cJisabuI05OylIRSJ+OG5CmzFxnjojUEJeCFi1njY1InhXrb0yHud9b1ifzweoN6YYOBecKs1gTOaT2bf+t4Wgzg3M0PmRVZ4F0OALsnh4T5+x7kFtiPcDKNpORi585JjKCZ4kczIF6oUKcwgC0kmIY97jtLqSLcXRkxHx5CDI6qz4XlRFs1ZbCUdSlzjdPZAkaBcNem1gIhWzkHkEnQIDAQAB"; npx:hasSignature "KRMl28WMaXZKmRg2zjeL7/p7F1OQvoQjPFoPoPWyLepELVt8gxCRqC4x760sn9/yYnAmdo+x9SJBsB4mU7DxppgNFjgm4Z/ptAaH4QdFnJkhyPgjzqCHEekKFr1cw6SGerZ4UZ6cMV/iqjMRx3Vs3Lm20qJbLYZaNvoXLggPtLPgClgShHXKk3y1WnkrS8RTZlzri+sDJTE0c5SnsR8Mmp0KfjIpxvUl8w3CxDcqfbiOvPqxV4qaesNvFXWIzWiMUg/l6iDqFwkfY7GgoE2rMsDMiNZXT4xoQrxQQJoQ0N9tVDqJt7t/Sq7VBJw8LqRxsBV5E3M/2fUePAdB5Rc+/A=="; npx:hasSignatureTarget this:; npx:signedBy . }