{
  "lesson": "26-relation-extraction-kg",
  "title": "Relation Extraction & Knowledge Graph Construction",
  "questions": [
    {
      "stage": "pre",
      "question": "What is the atomic unit of a knowledge graph?",
      "options": [
        "A token",
        "A POS tag",
        "A (subject, relation, object) triple",
        "A sentence"
      ],
      "correct": 2,
      "explanation": "KGs store information as (s, r, o) triples; aggregated triples form the graph."
    },
    {
      "stage": "pre",
      "question": "What does AEVS stand for in 2026 relation extraction?",
      "options": [
        "Aggregated Entity-Value Schema",
        "Async Entity Validation Service",
        "Auto-Encoder Vector Search",
        "Anchor-Extraction-Verification-Supplement: anchor spans, extract triples, verify against source, supplement coverage"
      ],
      "correct": 3,
      "explanation": "AEVS is the 2026 hallucination-mitigation framework for grounded RE."
    },
    {
      "stage": "check",
      "question": "Why must each triple carry source provenance (doc id + span)?",
      "options": [
        "Provenance is required by SPARQL",
        "It speeds up extraction",
        "Provenance changes the ontology",
        "Provenance lets you audit triples and reject hallucinations whose spans do not match the source text"
      ],
      "correct": 3,
      "explanation": "Provenance enables auditing and is the core of AEVS-style hallucination detection."
    },
    {
      "stage": "check",
      "question": "What does canonicalization of relations do?",
      "options": [
        "Adds embeddings",
        "Removes triples",
        "Maps surface verb phrases (e.g. 'was born in', 'is a native of') onto a fixed property id so the graph is queryable",
        "Translates the document"
      ],
      "correct": 2,
      "explanation": "Canonicalization collapses paraphrases into canonical KG property ids."
    },
    {
      "stage": "check",
      "question": "Why does relation extraction usually need coreference resolution first?",
      "options": [
        "Pronouns like 'he founded Apple' must be resolved to a named entity before triple extraction",
        "Coref normalizes case",
        "Coref provides positions",
        "Coref adds embeddings"
      ],
      "correct": 0,
      "explanation": "Without coref, RE attaches relations to pronouns instead of the underlying named entity."
    },
    {
      "stage": "post",
      "question": "Which choice trades open IE recall for graph queryability?",
      "options": [
        "Random sampling of triples",
        "Embedding-only graphs",
        "Mapping open-IE relations onto a closed ontology (e.g. Wikidata properties) before merging into the KG",
        "Skipping NER"
      ],
      "correct": 2,
      "explanation": "Closed ontologies make the graph queryable; the canonicalization step pays for itself downstream."
    },
    {
      "stage": "post",
      "question": "Why do many production KGs use temporal qualifiers (start/end time)?",
      "options": [
        "Required by RDF",
        "To remove NIL entities",
        "Faster SPARQL",
        "Many relations are time-bounded (employer, spouse, role); qualifiers prevent 'forever true' claims that go stale"
      ],
      "correct": 3,
      "explanation": "Time-bounded relations need qualifiers (e.g. Wikidata P580/P582) or facts go silently stale."
    },
    {
      "stage": "post",
      "question": "What is REBEL?",
      "options": [
        "A tokenizer",
        "A coreference model",
        "A seq2seq relation extractor that outputs triples already in Wikidata property ids",
        "A vector database"
      ],
      "correct": 2,
      "explanation": "REBEL (Babelscape) is a seq2seq RE model trained on distantly supervised Wikidata triples."
    }
  ]
}