Editing Knowledge Graphs (section)

== <span style="color: #FFFFFF;">Applying</span> ==
'''Building and querying a knowledge graph with Neo4j (Python driver):'''

<syntaxhighlight lang="python">
from neo4j import GraphDatabase

driver = GraphDatabase.driver("bolt://localhost:7687",
                               auth=("neo4j", "password"))

def create_knowledge_graph(session):
    """Create a simple research knowledge graph."""
    # Create entities and relationships using Cypher
    session.run("""
        MERGE (p:Person {name: 'Geoffrey Hinton'})
        MERGE (u:University {name: 'University of Toronto'})
        MERGE (a:Award {name: 'Nobel Prize in Physics'})
        MERGE (c:Concept {name: 'Backpropagation'})
        MERGE (p)-[:WORKED_AT {from: 1987, to: 2023}]->(u)
        MERGE (p)-[:RECEIVED {year: 2024}]->(a)
        MERGE (p)-[:PIONEERED]->(c)
        MERGE (c)-[:ENABLES]->(deep:Concept {name: 'Deep Learning'})
    """)

def find_award_winners_and_contributions(session):
    """Find Nobel Prize winners and what they pioneered."""
    result = session.run("""
        MATCH (p:Person)-[:RECEIVED]->(a:Award {name: 'Nobel Prize in Physics'})
        MATCH (p)-[:PIONEERED]->(c:Concept)
        RETURN p.name AS person, c.name AS contribution
        ORDER BY p.name
    """)
    return [dict(record) for record in result]

def multi_hop_query(session, concept_name):
    """Find all researchers connected to a concept within 2 hops."""
    result = session.run("""
        MATCH path = (p:Person)-[:PIONEERED|CONTRIBUTED_TO*1..2]->(c:Concept)
        WHERE c.name CONTAINS $concept
        RETURN p.name AS researcher, [node in nodes(path) | node.name] AS path_names
        LIMIT 10
    """, concept=concept_name)
    return [dict(record) for record in result]

with driver.session() as session:
    create_knowledge_graph(session)
    winners = find_award_winners_and_contributions(session)
    print(winners)
</syntaxhighlight>

; Knowledge graph construction pipeline
: '''Manual curation''' → Domain experts curate high-precision triples (medical ontologies, legal KGs)
: '''Crowd-sourced''' → Wikidata model: community contributes and validates
: '''Information extraction''' → NER + relation extraction from text corpora (automated, noisy)
: '''Web scraping + structured sources''' → Infoboxes, tables, linked data sources (Freebase model)
: '''Hybrid''' → Automated extraction + expert curation + community correction
</div>

<div style="background-color: #8B4500; color: #FFFFFF; padding: 20px; border-radius: 8px; margin-bottom: 15px;">