# Konstruktor: A Strong Baseline for Simple Knowledge Graph Question Answering

arXiv: https://arxiv.org/abs/2409.15902 · HTML: https://mlsanity.com/paper/2409.15902/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 26 of its 41 references that are in the map.
- First posted on arXiv 24 Sep 2024.

## Builds on (most cited first, 26 of 26)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [Scaling Instruction-Finetuned Language Models](https://mlsanity.com/paper/2210.11416/) (2022)
- [How Much Knowledge Can You Pack Into the Parameters of a Language Model?](https://mlsanity.com/paper/2002.08910/) (2020)
- [Unifying Large Language Models and Knowledge Graphs: A Roadmap](https://mlsanity.com/paper/2306.08302/) (2023)
- [Autoregressive Entity Retrieval](https://mlsanity.com/paper/2010.00904/) (2020)
- [A Comprehensive Capability Analysis of GPT-3 and GPT-3.5 Series Models](https://mlsanity.com/paper/2303.10420/) (2023)
- [Head-to-Tail: How Knowledgeable are Large Language Models (LLMs)? A.K.A. Will LLMs Replace Knowledge Graphs?](https://mlsanity.com/paper/2308.10168/) (2023)
- [Large-scale Simple Question Answering with Memory Networks](https://mlsanity.com/paper/1506.02075/) (2015)
- [Larger-Scale Transformers for Multilingual Masked Language Modeling](https://mlsanity.com/paper/2105.00572/) (2021)
- [Mintaka: A Complex, Natural, and Multilingual Dataset for End-to-End Question Answering](https://mlsanity.com/paper/2210.01613/) (2022)
- [Balancing Methods for Multi-label Text Classification with Long-Tailed Class Distribution](https://mlsanity.com/paper/2109.04712/) (2021)
- [Falcon 2.0: An Entity and Relation Linking Tool over Wikidata](https://mlsanity.com/paper/1912.11270/) (2019)
- [EARL: Joint Entity and Relation Linking for Question Answering over Knowledge Graphs](https://mlsanity.com/paper/1801.03825/) (2018)
- [SimpleQuestions Nearly Solved: A New Upperbound and Baseline Approach](https://mlsanity.com/paper/1804.08798/) (2018)
- [An Empirical Study of Pre-trained Language Models in Simple Knowledge Graph Question Answering](https://mlsanity.com/paper/2303.10368/) (2023)
- [Towards a Question Answering System over the Semantic Web](https://mlsanity.com/paper/1803.00832/) (2018)
- [RuBQ: A Russian Dataset for Question Answering over Wikidata](https://mlsanity.com/paper/2005.10659/) (2020)
- [Generative Relation Linking for Question Answering over Knowledge Bases](https://mlsanity.com/paper/2108.07337/) (2021)
- [Knowledge Graph Question Answering Leaderboard: A Community Resource to Prevent a Replication Crisis](https://mlsanity.com/paper/2201.08174/) (2022)
- [Strong Baselines for Simple Question Answering over Knowledge Graphs with and without Neural Networks](https://mlsanity.com/paper/1712.01969/) (2017)
- [Pretrained Transformers for Simple Question Answering over Knowledge Graphs](https://mlsanity.com/paper/2001.11985/) (2020)
- [Multilingual End to End Entity Linking](https://mlsanity.com/paper/2306.08896/) (2023)
- [Leveraging Semantic Parsing for Relation Linking over Knowledge Bases](https://mlsanity.com/paper/2009.07726/) (2020)
- [Semantic Answer Type and Relation Prediction Task (SMART 2021)](https://mlsanity.com/paper/2112.07606/) (2021)

## Built on by (most cited first, 3 of 3)

- [LLM-Independent Adaptive RAG: Let the Question Speak for Itself](https://mlsanity.com/paper/2505.04253/) (2025)
- [Will It Still Be True Tomorrow? Multilingual Evergreen Question Classification to Improve Trustworthy QA](https://mlsanity.com/paper/2505.21115/) (2025)
- [The benefits of query-based KGQA systems for complex and temporal questions in LLM era](https://mlsanity.com/paper/2507.11954/) (2025)

## Abstract (arXiv)

While being one of the most popular question types, simple questions such as "Who is the author of Cinderella?", are still not completely solved. Surprisingly, even the most powerful modern Large Language Models are prone to errors when dealing with such questions, especially when dealing with rare entities. At the same time, as an answer may be one hop away from the question entity, one can try to develop a method that uses structured knowledge graphs (KGs) to answer such questions. In this paper, we introduce Konstruktor - an efficient and robust approach that breaks down the problem into three steps: (i) entity extraction and entity linking, (ii) relation prediction, and (iii) querying the knowledge graph. Our approach integrates language models and knowledge graphs, exploiting the power of the former and the interpretability of the latter. We experiment with two named entity recognition and entity linking methods and several relation detection techniques. We show that for relation detection, the most challenging step of the workflow, a combination of relation classification/generation and ranking outperforms other methods. We report Konstruktor's strong results on four datasets.