ALL SPEAKERS
SESSIONS
SCHEDULE TBD
KEYNOTE
Context is a claim: What the papers miss about knowledge graphs.
AT A GLANCE
Role
Data Scientist
Organisation
Vahrenkamp IT Consulting
Category
Community
ABOUT THE SPEAKER
Christian is a freelance data scientist with an M.Sc. in Data Science. Since 2022 he has been building LLM and RAG systems that run air-gapped on open-weight models. His 2025 master's thesis applied GraphRAG to the decommissioning of nuclear facilities. Today he builds knowledge graph and agent systems for clients in regulated industries, currently a public-sector security authority, where every answer and result has to survive an audit.
TALK
Context is a claim: What the papers miss about knowledge graphs.
In the strictly regulated field of nuclear decommissioning, a misassigned regulation within a comprehensive risk and safety document leads to rejection by technical inspection authorities such as the TÜV - resulting in weeks of costly work interruptions and corrections. Most production knowledge graphs hide this failure mode: they treat time and location as extracted metadata, when in reality those are claims. Get context attribution right and you have the grounding layer for the whole compliance lifecycle - drafting domain experts trust, validation auditors can audit, corrections that compound. Three proven engineering patterns from real projects in nuclear and others: context attribution as a first-class claim, time as Allen-interval relations instead of just valid_from/valid_to and a hybrid ontology featuring an OTHERS bucket as a placeholder for unknown types in the corpus, as well as for types forming around new competence questions from user queries.
MORE VOICES
Other speakers at code.talks
See them live — and 100+ more.
One ticket, every track. Nov 4–5, 2026 at Kinopolis Hamburg.
Get your ticket
