Describe features of Natural Language Processing workloads on Azure →mediumMultiple ChoiceObjective-mapped
AI-900 Practice Question: Describe features of Natural Language Processing workloads on Azure
What is 'entity linking' in Azure AI Language and how does it differ from NER?
⚠ Common exam trap
Many exam-takers confuse entity linking with NER's simple labeling—candidates often think NER already handles disambiguation, but NER only tags entity types, while entity linking resolves which specific entity is meant.
Answer choices
Why each option matters
Answer the question above first, then reveal the full breakdown to understand why each option is right or wrong.
Correct answer & explanation
✓
Linking identified entities to knowledge base entries (e.g., Wikipedia) for disambiguation
Entity linking in Azure AI Language disambiguates identified entities by associating them with a unique identifier from a knowledge base, such as Wikipedia's Q-numbers. This differs from NER, which only labels entities (e.g., 'person', 'location') without resolving ambiguity—for example, 'Paris' could refer to a city or a person, and entity linking determines the correct one via the knowledge base.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
- ✗
Creating hyperlinks in a document that connect to related content online
Why it's wrong here
This option confuses the product-level artifact (an HTML anchor tag) with the semantic grounding operation performed by entity linking. Creating hyperlinks is a presentation-editing action that may point to any web page, regardless of whether the text refers to the same conceptual entity, and it does not involve knowledge-base disambiguation or unique identifier assignment. Entity linking generates a machine-readable reference to a canonical entity record, which might be rendered as a link afterward, but hyperlink creation itself is neither a necessary nor a sufficient condition for entity linking.
- ✓
Linking identified entities to knowledge base entries (e.g., Wikipedia) for disambiguation
Why this is correct
Entity linking is the task of mapping an ambiguous named entity mention (e.g., 'Mars') detected during named entity recognition (NER) to a unique, identifier-based entry in a knowledge base such as Wikipedia or Wikidata, thereby disambiguating 'the planet Mars' from 'Mars the chocolate bar'. The link attaches the mention to a knowledge graph node that carries canonical metadata, categories, and relationships, which enables downstream applications to reason about the entity with semantic precision rather than relying on surface-string matching alone.
- ✗
Connecting named entities across multiple documents to track the same person over time
Why it's wrong here
This option describes cross-document entity resolution (also called entity coreference resolution), which is a separate NLP task that determines whether mentions like 'John Smith' in one article and 'he' in another refer to the same real-world person. Entity linking, in contrast, does not track identity across documents; it grounds each mentioned entity to a single, canonical entry in a structured knowledge base such as Wikidata or Wikipedia, so ambiguity is resolved via a knowledge graph link, not via cross-document co-occurrence.
- ✗
Linking entity recognition results to downstream API calls for data enrichment
Why it's wrong here
This option describes application-level integration where the output of an NLP model is passed to an external service (for example, enriching a customer record by calling a CRM API). Entity linking is not about triggering or orchestrating API calls; it is the internal NLP process that selects a specific knowledge-base identifier for a mention using contextual cues and candidate ranking, and any downstream API usage would happen after the linking decision has already been made by the NLP model.
Visual reference
Go deeper
Related to this question
About these practice questions
Courseiva writes every AI-900 question from scratch — 985 in total, each with an explanation and a wrong-answer breakdown. None are copied from real exams or dumps. Learn why practice questions differ from exam dumps →
JA
Written by Johnson Ajibi, MSc IT Security
Senior Network & Security Engineer · founder of Courseiva
This AI-900 practice question is part of Courseiva's free Microsoft certification practice question bank. Courseiva provides original exam-style practice questions with explanations, topic-based practice, mock exams, readiness tracking, and study analytics to help learners prepare for the AI-900 exam.