A large number of published datasets (or sources) that follow Linked Data principles is currently available and this number grows rapidly. However, the major target of Linked Data, i.e., linking and integration, is not easy to achieve. In general, information integration is difficult, because (a) datasets are produced, kept, or managed by different organizations using different models, schemas, or formats, (b) the same real-world entities or relationships are referred with different URIs or names and in different natural languages,(c) datasets usually contain complementary information, (d) datasets can contain data that are erroneous, out-of-date, or conflicting, (e) datasets even about the same domain may follow different conceptualizations of the domain, (f) everything can change (e.g., schemas, data) as time passes. This article surveys the work that has been done in the area of Linked Data integration, it identifies the main actors and use cases, it analyzes and factorizes the integration process according to various dimensions, and it discusses the methods that are used in each step. Emphasis is given on methods that can be used for integrating several datasets. Based on this analysis, the article concludes with directions that are worth further research.

The CIDOC Conceptual Reference Model (CIDOC-CRM) is an ISO Standard ontology for the cultural domain that is used for enabling semantic interoperability between museums, libraries, archives and other cultural institutions. For leveraging CIDOC-CRM, several processes and tasks have to be carried out. It is therefore important to investigate to what extent we can automate these processes in order to facilitate interoperability. For this reason, in this paper, we describe the related tasks, and we survey recent works that apply machine learning (ML) techniques for reducing the costs related to CIDOC-CRM-based compliance and interoperability. In particular, we (a) analyze the main processes and tasks, (b) identify tasks where the recent advances of ML (including Deep Learning) would be beneficial, (c) identify cases where ML has been applied (and the results are successful/promising) and (d) suggest tasks that can benefit from applying ML. Finally, since the approaches that leverage both CIDOC-CRM data and ML are few in number, (e) we introduce our vision for the given topic, and (f) we provide a list of open CIDOC-CRM datasets that can be potentially used for ML tasks.

Browsing has been the core access method for the Web from its beginning. Analogously, one good practice for publishing data on the Web is to support dereferenceable URIs, to also enable plain web browsing by users. The information about one URI is usually presented through HTML tables (such as DBpedia and Wikidata pages) and graph representations (by using tools such as LODLive and LODMilla). In most cases, for an entity, the user gets all triples that have that entity as subject or as object. However, sometimes the number of triples is numerous. To tackle this issue, and to reveal similarity (and thus facilitate browsing), in this article we introduce an interactive similarity-based browsing system, called RDFsim, that offers “Parallel Browsing”, that is, it enables the user to see and browse not only the original data of the entity in focus, but also the K most similar entities of the focal entity. The similarity of entities is founded on knowledge graph embeddings; however, the indexes that we introduce for enabling real-time interaction do not depend on the particular method for computing similarity. We detail an implementation of the approach over specific subsets of DBpedia (movies, philosophers and others) and we showcase the benefits of the approach. Finally, we report detailed performance results and we describe several use cases of RDFsim.

In this paper, we present LODsyndesis, a suite of services over the datasets of the entire Linked Open Data Cloud, which offers fast, content-based dataset discovery and object co-reference. Emphasis is given on supporting scalable cross-dataset reasoning for finding all information about any entity and its provenance. Other tasks that can be benefited from these services are those related to the quality and veracity of data since the collection of all information about an entity, and the cross-dataset inference that is feasible, allows spotting the contradictions that exist, and also provides information for data cleaning or for estimating and suggesting which data are probably correct or more accurate. In addition, we will show how these services can assist the enrichment of existing datasets with more features for obtaining better predictions in machine learning tasks. Finally, we report measurements that reveal the sparsity of the current datasets, as regards their connectivity, which in turn justifies the need for advancing the current methods for data integration. Measurements focusing on the cultural domain are also included, specifically measurements over datasets using CIDOC CRM (Conceptual Reference Model), and connectivity measurements of British Museum data. The services of LODsyndesis are based on special indexes and algorithms and allow the indexing of 2 billion triples in around 80 min using a cluster of 96 computers.

In this article, we focus on the task of exploiting the capabilities of Large Language Models (LLMs) to generate SPARQL Queries for answering natural questions over cultural Knowledge Graphs (KGs) expressed according to the ISO standard ontology CIDOC-CRM. Since CIDOC-CRM is an event-based model, usually we have to follow long paths for answering a question, thereby, the challenge is how to construct the prompt for aiding the LLM to produce the right SPARQL query. We propose and comparatively evaluate methods based on the creation of ontology path patterns of a configurable path radius (or length). Then, we construct a new dedicated benchmark that includes 100 natural questions and the corresponding SPARQL queries over two real KGs from the cultural domain describing artworks. Finally, we present comparative results about the effectiveness and efficiency over the benchmark by using ChatGPT-3.5. The most effective method follows a two-stage process that predicts and uses the most appropriate path patterns of \(r\leq 4\) . This method achieves 3.5 \(\times\) higher accuracy than the baseline method (0.66 versus 0.19), that includes in the prompt only the list of properties and classes of the KG. Benchmark: https://github.com/mountanton/CIDOC-QA-using-LLMs