BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//pretalx//pretalx.coscup.org//coscup-2026//talk//LDNNEY
BEGIN:VTIMEZONE
TZID:CST
BEGIN:STANDARD
DTSTART:20000101T000000
RRULE:FREQ=YEARLY;BYMONTH=1
TZNAME:CST
TZOFFSETFROM:+0800
TZOFFSETTO:+0800
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
UID:pretalx-coscup-2026-LDNNEY@pretalx.coscup.org
DTSTART;TZID=CST:20260809T142000
DTEND;TZID=CST:20260809T145000
DESCRIPTION:Many of us know SPY×FAMILY — a “family” where each membe
 r has a hidden identity. At first\, it looks like a simple family story\, 
 but behind it is a network of hidden relationships.\n\nWhat if we could vi
 sualize such hidden relationships in knowledge?\n\nIn the open-source worl
 d\, we have access to a huge amount of unstructured data: Wikipedia\, docu
 ments\, and web pages. These sources are easy to read\, but difficult to r
 euse\, connect\, and track as their content changes over time. Relationshi
 ps may be hidden in text\, but their importance\, context\, and changes ov
 er time are even harder to see.\n\nThe core of this session is a step-by-s
 tep demonstration of how to turn a Wikipedia page into a knowledge graph u
 sing Neo4j and the Neo4j LLM Knowledge Graph Builder. The demonstration us
 es LLMs to extract entities and relationships from the Wikipedia page\, an
 d stores the extracted knowledge as a graph that can be explored\, compare
 d\, and reused.\n\nThen we will pick two versions of the same Wikipedia pa
 ge — past and present — and compare them as graphs. This allows us to 
 see how knowledge evolves: what was added\, what changed\, and how relatio
 nships grow over time.\n\nThis session is for developers\, data engineers\
 , and open-source contributors who want to build their own knowledge graph
  environment. By following the steps\, participants will learn how to star
 t from open data\, build a graph\, compare versions\, and apply the same a
 pproach to their own documents or web content.\n\nThis talk is not only ab
 out building graphs. It is about exploring knowledge\, comparing it\, and 
 understanding how it grows.\n\nEverything in this session is based on open
  data and open tools. No special dataset is required — just use the data
  already around you.
DTSTAMP:20260713T142420Z
LOCATION:TR410
SUMMARY:From SPY×FAMILY to Evolving Knowledge Graphs: Tracking Wikipedia C
 hanges with Neo4j and LLMs - Koji Annoura
URL:https://pretalx.coscup.org/coscup-2026/talk/LDNNEY/
END:VEVENT
END:VCALENDAR