What are the pitfalls when building a knowledge graph from unstructured text?

When constructing a Knowledge Graph (KG) from unstructured text, the following main challenges are encountered:

• Entity and relation extraction: Text often contains ambiguous or context-dependent terms, making it difficult to correctly identify entities and relationships.
• Coreference resolution: It is necessary to determine that different mentions (e.g., "he", "the director") refer to the same object.
• Handling synonyms and variations: Different words may denote the same concept, requiring normalization and merging.
• Noise and errors in text: Typos, grammatical errors, and informal style complicate analysis.
• Lack of structured templates: Complex NLP methods, such as neural network models, are needed to extract information.
• Scalability: Processing large volumes of text requires optimization and distributed computing.