The Connected Data Knowledge Graph: A Knowledge Graph for the community by the community
A Talk by Prashanth Rao , George Anadiotis , Richard Song , James Phare and Vassil Momtchev
About this Talk
If you want to know about Knowledge Graphs, then certainly you’re in the right place.
The Connected Data platform provides a Community, Events, and Thought Leadership for those who use the Relationships, Meaning and Context in Data to achieve great things.
We've been Connecting Data, People & Ideas since 2016. We focus on Knowledge Graphs, Graph Analytics / AI / Databases / Data Science and Semantic Technology.
Over the years, we have organized numerous events big and small, with our flagship London conference attracting thousands of attendees.
The collective knowledge of the leaders and innovators who have honored us with their presence is vast. Publicly available, but untapped.
There are 150+ expert and practical talks on Knowledge Graphs, Graph AI / Analytics / Data Science and Semantic Technology from previous Connected Data Conferences on our YouTube.
But people have little time to watch videos to learn and gather knowledge from experts and don’t know how to find the right videos. Thus, they miss opportunities to turn these great insights and best practices into something valuable.
A few months back, we started working on a project to create a curated Knowledge Graph based on our content. We wanted to make it easier to discover, explore, digest, combine and reuse our collective knowledge.
Join us as we share what we learned, what worked and what didn’t. We will share our experience on data processing and curation, metadata and data modeling, Knowledge Graph creation using Large Language Models, and building data pipelines. We will also show application demos.
Key Topics
- Data scraping and curation
- Using Large Language Models to generate a knowledge graph
- The importance of domain knowledge and a domain model
- Going from metadata to a domain model
- Data modeling and meta-modeling for graphs
- Building a data pipeline
- Question answering on the knowledge graph
Target Audience
- Engineers
- Analysts
- Managers
- Anyone interested in using content creatively
Goals
Learn how to set up a data pipeline, a data model and Large Language Models to help process content to create a knowledge graph from scratch.
Session outline:
- Introduction (10 minutes)
- Connected Data and our source material
- The workflow
- Building the Knowledge Graph (50 minutes)
- Data scraping and curation
- Using Large Language Models to generate a knowledge graph
- The importance of a domain knowledge and a domain model
- Going from metadata to a domain model
- Data modeling and meta-modeling for graphs
- Building a data pipeline
- Using the Knowledge Graph
- Demos (60 minutes)
- In-house
- Epsilla
- Graphwise
Format
This session is structured as an interactive presentation in 2 parts. The team will engage with participants after each component of the presentation.
The first part will be in a lecture format. The team will walk participants through the different components of the project. We will go over the thinking behind each component and share lessons learned.
The second part will be in a demo format. Different applications built on top of the Connected Data Knowledge Graph will be showcased. Application builders will show how everything works, and share their experience working with the Connected Data Knowledge Graph.
Level
Beginner - Intermediate
Prerequisite Knowledge
None. Some familiarity with data modeling would be beneficial.
About The Speakers
AI Engineer, Kùzu Inc.
Prashanth Rao is an AI engineer at Kùzu Inc. Over the last several years, he's worked with numerous data systems, including graph DBs, with a focus on data engineering, analytics and machine learning to power a variety of applications.
Connected Data London
Got tech, data, AI and media, and not afraid to use them I help people: * Map and understand complex domains to make better decisions * Design, implement and monitor models, processes & systems to achieve goals * Craft communication strategies and outreach initiatives to grow awareness & market
Co-Founder and CEO, Epsilla
Richard leads Epsilla in helping businesses develop production-ready RAG systems, enabling them to extract transformative insights from large-scale proprietary data and drive AI-powered innovation.
CEO, Neural Alpha
James co-founded Connected Data in 2016 having discovered the wonderful world of graphs, ontologies and related innovations around 2010. He uses these technologies on a daily basis in his consultancy work as CEO of Neural Alpha - a sustainability focused consultancy leveraging Connected Data tech.
We’re a cloud tech company that provides organisations around the world with computing infrastructure and software to help them innovate, unlock efficiencies and become more effective. We also created the world’s first – and only – autonomous database to help organise and secure our customers’ data.
