Knowledge Graph — References

Construction from text, identity resolution, and the standards for provenance and validation.

Construction and survey

• Knowledge Graphs — Aidan Hogan, Eva Blomqvist, Michael Cochez, Claudia d'Amato, Gerard de Melo, Claudio Gutierrez, Sabrina Kirrane, José Emilio Labra Gayo, Roberto Navigli, Sebastian Neumaier, Axel-Cyrille Ngonga Ngomo, Axel Polleres, Sabbir M. Rashid, Anisa Rula, Lukas Schmelzeisen, Juan Sequeda, Steffen Staab and Antoine Zimmermann, ACM Computing Surveys, 2021. The comprehensive survey: construction, identity, quality and refinement. Cited by name.
• Knowledge Vault: A Web-Scale Approach to Probabilistic Knowledge Fusion — Xin Luna Dong, Evgeniy Gabrilovich, Geremy Heitz, Wilko Horn, Ni Lao, Kevin Murphy, Thomas Strohmann, Shaohua Sun and Wei Zhang, ACM KDD, 2014. Fusing extracted assertions from many sources with explicit confidence, and the argument for storing evidence rather than conclusions. Cited by name.
• DBpedia: A Nucleus for a Web of Open Data — Sören Auer, Christian Bizer, Georgi Kobilarov, Jens Lehmann, Richard Cyganiak and Zachary Ives, ISWC, 2007. Extraction of a graph from semi-structured text at scale, and the identifier conventions that made it reusable. Cited by name.

Identity resolution

• Duplicate Record Detection: A Survey — Ahmed K. Elmagarmid, Panagiotis G. Ipeirotis and Vassilios S. Verykios, IEEE Transactions on Knowledge and Data Engineering, 2007. Blocking, comparison and decision models for deciding that two records describe one thing. Cited by name.
• A Theory for Record Linkage — Ivan P. Fellegi and Alan B. Sunter, Journal of the American Statistical Association, 1969. The probabilistic framework underneath most resolution systems, including the explicit clerical-review band between the match and non-match thresholds. Cited by name.

Provenance, validation and modelling

• PROV-O: The PROV Ontology — the W3C vocabulary for recording what produced an assertion, by what activity, from what source.
• SHACL: Shapes Constraint Language — validating that a graph conforms to a declared shape, which is how schema enforcement is achieved where the store does not provide it.
• RDF 1.1 Concepts and Abstract Syntax — the data model, including named graphs, which is the usual mechanism for attaching provenance to a statement.
• Time Ontology in OWL — temporal entities and intervals, for expressing the period over which a relation is claimed to hold.

No verified reference is recorded for replaying a curated correction layer over a rebuilt extraction, or for identity stability across extraction-model upgrades. These are engineering practice without published study.