Generative AI provides an innovative and exciting way to manage knowledge and data at any scale; for small projects, at the enterprise level, and even at a world wide web scale. It is tempting to think that Generative AI has made other knowledge-based technologies obsolete; that anything we wanted to do with knowledge-based systems, knowledge graphs or even expert systems can instead be done with Generative AI. Our position is counter to that conclusion.Our practical experience on implementing enterprise question answering systems using Generative AI has shown that Knowledge Graphs support this infrastructure in multiple ways: they provide a formal framework to evaluate the validity of a query generated by an LLM, serve as a foundation for explaining results, and offer access to governed and trusted data. In this position paper, we share our experience, present industry needs, and outline the opportunities for future research contributions.

There is increasing evidence that question-answering (QA) systems with Large Language Models (LLMs), which employ a knowledge graph representation of an enterprise SQL database (Text-to-SPARQL), achieve higher accuracy compared to systems that answer questions directly on SQL databases (Text-to-SQL). The objective of this research is to further improve the accuracy of these LLM Question Answering systems. Our approach, Ontology-based Query Check (OBQC), is to check the LLM generated SPARQL query against the semantics specified by the ontology. A query will be flagged as incorrect and prevented from execution if it does not align with the ontological semantics. The study also explores the LLM’s capability in repairing a SPARQL query given an explanation of the error (LLM Repair). Our methods are evaluated using the chat with the data benchmark. The primary finding is our method further increases the accuracy overall by 21.59

Enterprise applications of Large Language Models (LLMs) hold promise for question answering on enterprise SQL databases. However, the extent to which LLMs can accurately respond to enterprise questions in such databases remains unclear, given the absence of suitable Text-to-SQL benchmarks tailored to enterprise settings. Additionally, the potential of Knowledge Graphs (KGs) to enhance LLM-based question answering by providing business context is not well understood. This study aims to evaluate the accuracy of LLM-powered question answering systems in the context of enterprise questions and SQL databases, while also exploring the role of knowledge graphs in improving accuracy. To achieve this, we introduce a benchmark comprising an enterprise SQL schema in the insurance domain, a range of enterprise queries encompassing reporting to metrics, and a contextual layer incorporating an ontology and mappings that define a knowledge graph. Our primary finding reveals that question answering using GPT-4, with zero-shot prompts directly on SQL databases, achieves an accuracy of 16%. Notably, this accuracy increases to 54% when questions are posed over a Knowledge Graph representation of the enterprise SQL database. Therefore, investing in Knowledge Graph provides higher accuracy for LLM powered question answering systems.

SemTab 2023 was the fifth edition of the Semantic Web Challenge on Tabular Data to Knowledge Graph Matching, collocated with the 22 nd International Semantic Web Conference (ISWC) and the 18 th Ontology Matching (OM) Workshop. SemTab provides a framework to conduct a systematic evaluation of state-of-the-art semantic table interpretation systems. In this paper, we give an overview of the 2023 edition of the challenge and summarize the results.

Property graphs have reached a high level of maturity, witnessed by multiple robust graph database systems as well as the ongoing ISO standardization effort aiming at creating a new standard Graph Query Language (GQL). Yet, despite documented demand, schema support is limited both in existing systems and in the first version of the GQL Standard. It is anticipated that the second version of the GQL Standard will include a rich DDL. Aiming to inspire the development of GQL and enhance the capabilities of graph database systems, we propose PG-Schema, a simple yet powerful formalism for specifying property graph schemas. It features PG-Types with flexible type definitions supporting multi-inheritance, as well as expressive constraints based on the recently proposed PG-Keys formalism. We provide the formal syntax and semantics of PG-Schema, which meet principled design requirements grounded in contemporary property graph management scenarios, and offer a detailed comparison of its features with those of existing schema languages and graph database systems.

Incomplete data, in the form of null values, has been extensively studied since the inception of the relational model in the 1970s. Anecdotally, one hears that the way in which SQL, the standard language for relational databases, handles nulls creates a myriad of problems in everyday applications of database systems. To the best of our knowledge, however, the actual shortcomings of SQL in this respect, as perceived by database practitioners, have not been systematically documented, and it is not known if existing research results can readily be used to address the practical challenges. Our goal is to collect and analyze the shortcomings of nulls and their treatment by SQL, and to re-evaluate existing research in this light. To this end, we designed and conducted a survey on the everyday usage of null values among database users. From the analysis of the results we reached two main conclusions. First, null values are ubiquitous and relevant in real-life scenarios, but SQL's features designed to deal with them cause multiple problems. The severity of these problems varies depending on the SQL features used, and they cannot be reduced to a single issue. Second, foundational research on nulls is misdirected and has been addressing problems of limited practical relevance. We urge the community to view the results of this survey as a way to broaden the spectrum of their researches and further bridge the theory-practice gap on null values.

At the foundation of any knowledge graph is the principle of first applying a graph abstraction to data, resulting in an initial data graph. We now discuss a selection of graph-structured data models that are commonly used in practice to represent data graphs. We then discuss the primitives that form the basis of graph query languages used to interrogate such data graphs.

In this chapter, we discuss some of the most prominent knowledge graphs that have emerged in the past years. We begin by discussing open knowledge graphs, most of which have been published on the Web per the guidelines and protocols described in Chapter 9. We later discuss enterprise knowledge graphs that have been created by companies from diverse industries for a wide range ofapplications.

In this chapter, we discuss the principal techniques by which knowledge graphs can be created and subsequently enriched from diverse sources of legacy data that range from plain text to structured formats (and anything in between). The appropriate methodology to follow when creating a knowledge graph depends on the actors involved, the domain, the envisaged applications, the available data sources, etc. Generally speaking, however, the flexibility of knowledge graphs lends itself to starting with an initial core that can be incrementally enriched from other sources as required (typically following an Agile [Hunt and Thomas, 2003] or “pay-as-you-go” [Se-queda et al., 2019] methodology). For our running example, we assume that the tourism board decides to build a knowledge graph from scratch, aiming to initially describe the main tourist attractions–places, events, etc.–in Chile in order to help visiting tourists identify those that most interest them. The board decides to postpone adding further data, like transport routes, reports of crime, etc., for a later date.

As humans, we can deduce more from the data graph of Figure 2.1 than what the edges explicitly indicate. We may deduce, for example, that the $${\rm{\tilde N}}$$ am festival ((eidis)) will be located in Santiago, even though the graph does not contain an edge (eidis)— location →(santiago). We may further deduce that the cities connected by flights must have some airport nearby, even though the graph does not contain nodes referring to these airports. In these cases, given the data as premises, and some general rules about the world that we may know a priori, we can use a deductive process to derive new data, allowing us to know more than what is explicitly given by the data. These types of general premises and rules, when shared by many people, form part of “commonsense knowledge” [McCarthy, 1990]; conversely, when rather shared by a few experts in an area, they form part of “domain knowledge,” where, for example, an expert in biology may know that hemocyanin is a protein containing copper that carries oxygen in the blood of some species of Mollusca and Arthropoda.

While deductive knowledge is characterized by precise logical consequences, inductively acquiring knowledge involves generalizing patterns from a given set of input observations, which can then be used to generate novel but potentially imprecise predictions. For example, from a large data graph with geographical and flight information, we may observe the pattern that almost all capital cities of countries have international airports serving them, and hence predict that if Santiago is a capital city, it likely has an international airport serving it; however, the predictions drawn from this pattern do not hold for certain, where, e.g., Vaduz, the capital city of Liechtenstein, has no (international) airport serving it. Hence, predictions will often be associated with a level of confidence; for example, we may say that a capital has an international airport in 187/195 of cases, offering a confidence of 0.959 for predictions made with that pattern. We then refer to knowledge acquired inductively as inductive knowledge, which includes both the models used to encode patterns, as well as the predictions made by those models. Though fallible, inductive knowledge can be highly valuable.

SemTab 2022 was the fourth edition of the Semantic Web Challenge on Tabular Data to Knowledge Graph Matching, successfully collocated with the 21 st International Semantic Web Conference (ISWC) and the 17 th Ontology Matching (OM) Workshop. SemTab provides a common framework to conduct a systematic evaluation of state-of-the-art systems. In this paper, we give an overview of the 2022’s edition of the challenge and summarize the results

This report documents the program and the outcomes of Dagstuhl Seminar 22031 “Bringing Graph Databases and Network Visualization Together”. Due to the ongoing restrictions caused by the COVID-19 pandemic, this purely on-site seminar had a reduced number of participants. Twenty-two researchers and practitioners from the Network Visualization and Graph Database communities met to initiate collaborative work and exchange between the two communities. The seminar served to establish a common understanding of the state of the art and the terminology in both communities

In this chapter we describe extensions of the data graph–relating to schema, identity, and context–that provide additional structures for accumulating knowledge. Henceforth, we refer to a data graph as a collection of data represented as nodes and edges using one of the models discussed in Chapter 2. We refer to a knowledge graph as a data graph potentially enhanced with representations of schema, identity, context, ontologies, and/or rules. These additional representations may be embedded in the data graph, or layered above. Representations for schema, identity and context are discussed now, while ontologies and rules will be discussed in Chapter 4.

Knowledge graphs (KGs) have emerged as a compelling abstraction for organizing the world's structured knowledge and for integrating information extracted from multiple data sources. They are also beginning to play a central role in representing information extracted by AI systems, and for improving the predictions of AI systems by giving them knowledge expressed in KGs as input. The goals of this article are to (a) introduce KGs and discuss important areas of application that have gained recent prominence; (b) situate KGs in the context of the prior work in AI; and (c) present a few contrasting perspectives that help in better understanding KGs in relation to related technologies.

Ensuring the success of big graph processing for the next decade and beyond.

Tracking the historical events that lead to the interweaving of data and knowledge.