Structured Prompt Interrogation and Recursive Extraction of Semantics (SPIRES): a method for populating knowledge bases using zero-shot learning
Open accessThe DOI matches its Crossref record; 7 of the 7 references it cites were found in a registry or an index.
Abstract
Motivation: Creating knowledge bases and ontologies is a time consuming task that relies on manual curation. AI/NLP approaches can assist expert curators in populating these knowledge bases, but current approaches rely on extensive training data, and are not able to populate arbitrarily complex nested knowledge schemas. Results: Here we present Structured Prompt Interrogation and Recursive Extraction of Semantics (SPIRES), a Knowledge Extraction approach that relies on the ability of Large Language Models (LLMs) to perform zero-shot learning and general-purpose query answering from flexible prompts and return information conforming to a specified schema. Given a detailed, user-defined knowledge schema and an input text, SPIRES recursively performs prompt interrogation against an LLM to obtain a set of responses matching the provided schema. SPIRES uses existing ontologies and vocabularies to provide identifiers for matched elements. We present examples of applying SPIRES in different domains, including extraction of food recipes, multi-species cellular signaling pathways, disease treatments, multi-step drug mechanisms, and chemical to disease relationships. Current SPIRES accuracy is comparable to the mid-range of existing Relation Extraction methods, but greatly surpasses an LLM’s native capability of grounding entities with unique identifiers. SPIRES has the advantage of easy customization, flexibility, and, crucially, the ability to perform new tasks in the absence of any new training data. This method supports a general strategy of leveraging the language interpreting capabilities of LLMs to assemble knowledge bases, assisting manual knowledge curation and acquisition while supporting validation with publicly-available databases and ontologies external to the LLM. Availability and implementation: SPIRES is available as part of the open source OntoGPT package: https://github.com/monarch-initiative/ontogpt.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Language Models are Few-Shot Learners
Brown, T. B., Mann, B., Ryder, N., Subbiah, M., Kaplan, J., Dhariwal, P., Neelakantan, A., Shyam, P., Sastry, G., Askell, A., et al. (2020) · arXiv · doi:10.48550/arxiv.2005.14165 · Cited by 23,372
DrugBank 5.0: a major update to the DrugBank database for 2018
Wishart, D. S., Feunang, Y. D., Guo, A. C., Lo, E. J., Marcu, A., Grant, J. R., Sajed, T., Johnson, D., Li, C., Sayeeda, Z., et al. (2018) · Nucleic Acids Research · doi:10.1093/nar/gkx1037 · Cited by 8,404 · cited 1×
“Grounding was performed using multiple ontologies beyond MeSH, including three resources for chemical and drug information: Chemical Entities of Biological Interest (ChEBI) [23], DrugBank [24], and MedDRA [25] (See Table S1 for a full list of external resources used for grounding).”
MethodThe Gene Ontology Resource: 20 years and still GOing strong
The Gene Ontology Consortium (2019) · Nucleic Acids Research · doi:10.1093/nar/gky1055 · Cited by 4,747 · cited 1×
“In the life sciences, KBs such as the Gene Ontology (GO) [2] and the Reactome biological pathway KB [3] contain extensive curated knowledge detailing cellular mechanisms that involve interacting gene products and molecules.”
BackgroundLLaMA: Open and Efficient Foundation Language Models
Touvron, H., Lavril, T., Izacard, G., Martinet, X., Lachaux, M.-A., Lacroix, T., Rozière, B., Goyal, N., Hambro, E., Azhar, F., et al. (2023) · arXiv · doi:10.48550/arxiv.2302.13971 · Cited by 4,602
BioGPT: generative pre-trained transformer for biomedical text generation and mining
Luo, R., Sun, L., Xia, Y., Qin, T., Zhang, S., Poon, H., & Liu, T.-Y. (2022) · Briefings in Bioinformatics · doi:10.1093/bib/bbac409 · Cited by 1,150 · cited 2×
“For comparison, Luo et al. report an F-score of 44.98 on BC5CDR with their biomedical domain-specific, trained-from-scratch BioGPT model [9].”
BackgroundInfluentialWhat BERT Is Not: Lessons from a New Suite of Psycholinguistic Diagnostics for Language Models
Ettinger, A. (2020) · Transactions of the Association for Computational Linguistics · doi:10.1162/tacl_a_00298 · Cited by 511 · cited 1×
“These techniques have known limitations, such as being prone to hallucinations [5] (i.e., generating incorrect statements) and insensitivity to negations [6].”
BackgroundMungall, C. J., McMurry, J. A., Köhler, S., Balhoff, J. P., Borromeo, C., Brush, M., Carbon, S., Conlin, T., Dunn, N., Engelstad, M., et al. (2017) · Nucleic Acids Research · doi:10.1093/nar/gkw1128 · Cited by 441
Self-citation
Cited by
The future landscape of large language models in medicine
Clusmann, J., Kolbinger, F. R., Muti, H. S., Carrero, Z. I., Eckardt, J.-N., Laleh, N. G., Löffler, C. M. L., Schwarzkopf, S.-C., Unger, M., Veldhuizen, G. P., et al. (2023) · Communications Medicine · doi:10.1038/s43856-023-00370-1 · Cited by 1,045
“For example, LLMs can be used to ef fi ciently extract data of interest from vast, unstructured text fi les or images, which is a tedious task that can lead to errors if it is done manually 51 .”
MethodOpportunities and Challenges for ChatGPT and Large Language Models in Biomedicine and Health
Tian, S., Jin, Q., Yeganova, L., Lai, P.-T., Zhu, Q., Chen, X., Yang, Y., Chen, Q., Kim, W., Comeau, D. C., et al. (2023) · Briefings in Bioinformatics · doi:10.1093/bib/bbad493 · Cited by 359
ChatGPT for shaping the future of dentistry: the potential of multi-modal large language model
Huang, H., Zheng, O., Wang, D., Yin, J., Wang, Z., Ding, S., Yin, H., Xu, C., Yang, R., Zheng, Q., et al. (2023) · International Journal of Oral Science · doi:10.1038/s41368-023-00239-y · Cited by 324
“Inherently, these LLMs operate as sophisticated pattern-matching machines without a genuine understanding of the data they are trained on, which occasionally leads to nonsensical or inappropriate responses.(103) Compounding these issues, they lack the capacity to validate the information they generate, remaining incap…”
BackgroundEvaluation of large language models for discovery of gene set function
Hu, M., Alkhairy, S., Lee, I., Pillich, R. T., Fong, D., Smith, K., Bachelder, R., Ideker, T., & Pratt, D. (2025) · Nature Methods · doi:10.1038/s41592-024-02525-x · Cited by 104
“Best practices for formulating this prompt are the subject of ongoing experimentation 39–42 ; here, our prompt was engineered to capture desired properties of the results to be generated, including guiding phrases such as “After completing your analysis, propose a short descriptive name for the…”
Romero, O. J., Zimmerman, J., Steinfeld, A., & Tomasic, A. (2023) · arXiv · doi:10.48550/arxiv.2308.09830 · Cited by 44
Gilani, K., Verket, M., Peters, C., Dumontier, M., Rocca, H.-P. B.-L., & Urovi, V. (2025) · Computers in Biology and Medicine · doi:10.1016/j.compbiomed.2025.110745 · Cited by 5
Rosetta Statements: simplifying FAIR knowledge graph construction with a user-centred approach
Vogt, L., Farfar, K. E., Karanth, P., Konrad, M., Oelen, A., Prinz, M., & Strömert, P. (2026) · Database · doi:10.1093/database/baag030 · Cited by 4
Metadata
- Authors
- Caufield, J. H., Hegde, H., Emonet, V., Harris, N. L., Joachimiak, M. P., Matentzoglu, N., Kim, H., Moxon, S., Reese, J. T., Haendel, M. A., Robinson, P. N., & Mungall, C. J.
- Venue
- Bioinformatics
- Publisher
- Oxford University Press (OUP)
- Published
- 2024-02-21
- Volume
- 40
- Issue
- 3
- ISSN
- 1367-4803 (ISSN-L)
- 1367-4811
- OpenAlex
- W4392619039
- Cited by
- 120
- References
- 7
- FWCI
- 12.78
- Type
- journal article
- Language
- en
- Open access
- gold
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.