Practice vocabulary for building knowledge graphs: entity extraction, relation extraction, entity linking, coreference resolution, and open knowledge graphs like Wikidata and DBpedia.
0 / 12 completed
1 / 12
What is 'entity extraction' in the context of knowledge graph construction?
Entity extraction (also called Named Entity Recognition, NER) is the NLP task of detecting spans in text that refer to real-world entities and assigning them types. It is the first step in populating a knowledge graph from text sources.
2 / 12
How would you explain 'entity linking' to a colleague?
Entity linking (also called entity disambiguation) maps a text mention to a specific knowledge base entry. 'Apple' could refer to the fruit or the company — entity linking resolves this ambiguity using context.
3 / 12
What problem does 'coreference resolution' solve during knowledge graph construction?
Coreference resolution groups all mentions in a document that refer to the same entity. Without it, 'Tesla' and 'the company' in the same paragraph might generate separate, unconnected nodes in the graph.
4 / 12
What is Wikidata in the context of open knowledge graphs?
Wikidata is one of the largest open knowledge graphs, containing hundreds of millions of statements about entities worldwide. It is machine-readable, multilingual, and freely licensed, making it a common seed for domain-specific knowledge graph construction.
5 / 12
What does 'populating a knowledge graph' typically involve?
Populating (or building) a knowledge graph covers the full construction pipeline: sourcing data, extracting entities and relations, resolving entity identity, mapping to an ontology, and loading triples into the graph. Each step has its own set of NLP and data engineering vocabulary.
6 / 12
Alex: 'I'm seeing inconsistent results when querying the knowledge graph for user profiles. Sometimes it returns data about their hobbies, and other times it doesn't. What could be causing this?'
Alex's question highlights a potential issue with entity extraction. If the system isn't correctly identifying which attributes are associated with a user (e.g., hobbies), it won't populate the knowledge graph accurately and inconsistent results will occur. Options C and D point to broader performance issues, not the core problem of flawed data ingestion.
7 / 12
Sarah (in a Slack channel) asks: 'How do we ensure that different systems referencing the same entity – like our CRM and our marketing automation platform – are pointing to the *same* data?'. What is the most appropriate response?
Sarah's question centers on the critical need for entity linking. Entity linking resolves variations in how an entity is referred to (e.g., 'John Smith', 'Mr. Smith') and maps them to a single, consistent representation within the knowledge graph – this ensures data integrity across different systems. Option A is insufficient; simply using naming conventions doesn't guarantee consistency.
8 / 12
David: 'We're using a graph database to represent customer relationships. I need to add a new node representing a product and connect it to existing nodes for customers who have purchased that product. What's the most efficient way to do this?'
This question assesses understanding of core knowledge graph construction techniques. The correct answer focuses on creating relationships (edges) between nodes – the fundamental building block. Options A and D present simplified or overly complex solutions; B incorrectly suggests manual updates are efficient.
9 / 12
PR Description: 'Adding a new entity 'PaymentMethod' to the knowledge graph. This includes mapping existing customer data fields like 'creditCardNumber', 'bankAccountDetails' to this new node type and establishing relationships indicating which customers use which payment methods. The schema update also incorporates a validation rule to ensure all PaymentMethod nodes adhere to GDPR compliance standards.' What is the primary purpose of adding the 'validation rule' mentioned in this PR description?
The question tests understanding of the importance of validation within a knowledge graph context. While increased size or faster queries might be benefits, the core purpose is data quality and compliance – crucial for maintaining reliable information and avoiding legal issues.
10 / 12
Slack Message: 'Hey team, I'm struggling to understand how the knowledge graph is handling product recommendations. The system keeps suggesting products that users haven't actually purchased or viewed! I suspect there might be an issue with linking product attributes to user behavior data.' What technique would most directly address this problem?
This scenario highlights a common problem in recommendation systems – inaccurate linking. The correct answer emphasizes entity linking, connecting product data with user behavior to create meaningful relationships within the knowledge graph.
11 / 12
Standup Update: 'I've been working on integrating our CRM data into the knowledge graph. We're using a tool called 'GraphWeaver' to automatically extract entities like customer names and addresses. However, I'm encountering challenges with disambiguation – sometimes GraphWeaver incorrectly identifies multiple customers with the same name.' What is 'disambiguation' in this context?
This question focuses on a critical aspect of knowledge graph construction – dealing with ambiguous data. Disambiguation refers to the process of resolving conflicting information and ensuring each entity has a clear, singular representation within the graph.
12 / 12
Code Review Comment: 'This code adds a new node representing a 'Book' to the knowledge graph. The linking logic is implemented using a simple string matching algorithm based on book titles. However, this approach doesn't handle variations in title formatting or typos effectively.' What would be a more robust solution for entity linking?
This scenario tests understanding of the limitations of simple approaches to entity linking. Fuzzy matching and synonym dictionaries are essential for handling real-world data variability – a key challenge in knowledge graph construction.
What will I practise in "Knowledge Graph Construction Vocabulary"?
Practice vocabulary for building knowledge graphs: entity extraction, relation extraction, entity linking, coreference resolution, and open knowledge graphs like Wikidata and DBpedia.
How many exercises are in this module?
This module has 12 multiple-choice exercises, each with instant feedback and a full explanation of the correct answer.
Is this exercise free to use?
Yes. Every exercise on CoderSlingo, including this one, is free to use with no account, sign-up, or paywall.
Do I need to create an account to do these exercises?
No account is required. Just click an option to answer — your score for this session is tracked automatically in the progress bar above.
What happens if I choose the wrong answer?
You'll immediately see which answer was correct, plus a full explanation covering the vocabulary and reasoning behind it — mistakes are where most of the learning happens.
Can I retry the exercises if I want a higher score?
Yes — use the "Try again" button on the results screen to reset and go through all the questions again.
Is my progress saved if I close the page?
No. Progress is tracked only for your current visit; reloading or leaving the page resets the counter. This keeps the exercise simple and account-free.
Where can I find more Knowledge Graph Vocabulary exercises?
Browse the full Knowledge Graph Vocabulary hub for related drills, or check the "Next up" link below to continue with a connected topic.
How is this different from reading an article on the same topic?
Articles explain vocabulary and concepts in prose; this exercise tests and reinforces that vocabulary through active recall with immediate feedback — the two work best together.
Who writes these exercises?
Every exercise is written by the CoderSlingo team, drawing on real workplace English used in IT roles, then reviewed for accuracy and clarity.