The Ontology Pipeline™, Refresh

2026-01-05 · Source: Modern Data 101 · Field: Technology & Digital — Artificial Intelligence & Machine Learning, Data Science & Analytics · Depth: Advanced, long

Summary

Jessica Talisman, a Semantic Engineer and Information Architect with over 25 years of experience, presents a refresh of her Ontology Pipeline™ framework, originally published in January 2025. This framework, derived from library and information science and the Semantic Web, provides a structured methodology for building semantic knowledge infrastructures, progressing from controlled vocabularies to taxonomies, thesauri, ontologies, and knowledge graphs. The update addresses the increased demand and confusion surrounding semantic systems since the public release of ChatGPT in November 2022, emphasizing that while AI can accelerate the work, human judgment and expertise are critical. Talisman highlights the current skills gap in semantics engineering and proposes extending the pipeline with formal governance and strategic AI partnerships to ensure coherence and reliability in evolving knowledge systems.

Key takeaway

For CTOs and VP of Engineering/Data grappling with AI hallucinations and unreliable RAG implementations, recognize that robust semantic knowledge infrastructure is non-negotiable. Invest in structured methodologies like the Ontology Pipeline™ and prioritize upskilling your teams in semantic engineering and knowledge governance. Relying solely on AI-generated taxonomies without human validation and a clear methodology will lead to predictable system failures and wasted resources.

Key insights

Effective semantic knowledge infrastructure requires a structured pipeline, human expertise, and robust governance, not just AI-generated outputs.

Principles

• Build semantic systems progressively: vocabulary to knowledge graph.
• Human judgment is essential for validating AI-generated knowledge.
• Governance is an engineering practice, not an afterthought.

Method

The Ontology Pipeline™ framework involves sequential stages: controlled vocabulary, metadata standards, taxonomy, thesaurus, ontology, and knowledge graph, now augmented by formal governance and AI partnerships.

In practice

• Prioritize foundational data hygiene before advanced semantic modeling.
• Use AI to accelerate, not replace, human expertise in ontology work.
• Implement formal governance to maintain ontology coherence over time.

Topics

• Ontology Pipeline
• Semantic Knowledge Systems
• Knowledge Graphs
• AI Collaboration
• Knowledge Governance

Best for: CTO, VP of Engineering/Data, AI Architect, Data Engineer, Director of AI/ML

Related on AIssential

• The Ontology Pipeline™, Refresh — Effective semantic knowledge infrastructure requires a disciplined, sequential approach, augmented by AI and robust governance.
• Steal This Deck — Reliable agentic AI requires robust knowledge infrastructure, not just data, to overcome current productivity and hallucination issues.
• Semantic Foundations for Reliable Enterprise AI — Semantic clarity in data, achieved through robust data contracts and ontologies, is crucial for reliable enterprise AI outputs.
• Ontologies Are the Intentional Core of a True Knowledge Graph — Formal ontologies provide the stable, intentional semantic backbone essential for reliable enterprise AI and knowledge graphs.
• The Semantic Infrastructure Opportunity: Building Meaningful Operational Frameworks — Semantic infrastructure, especially entity resolution, makes ontology work measurably operational and critical for AI systems.
• Knowledge Graph Re-engineering Along the Ontological Continuum (extended version) — The "ontological continuum" offers a principled framework to describe and transform diverse knowledge graph modeling practices.

Open in AIssential →

Editorial summary, takeaway, and curation by AIssential. Original article published by Modern Data 101.