# Relational Triplet Extraction on NYC Source: [Relational Triplet Extraction on NYC]() Collection index: [llms.txt]() Data updated: 2026-02-26T05:45:45.351Z Evaluation of Relational Triplet Extraction performance on the NYC dataset, measured using GPT accuracy, GPT confidence, and Human accuracy. A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. | Scope | Recorded value | | --- | --- | | Task | Relational Triplet Extraction (RTE) | | Dataset (including any stated split) | NYC | | Metric | GPT Accuracy | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 32 of 32 | | Coverage | All results currently returned for this benchmark | Evaluation settings may differ between results. The original papers and recorded configurations are needed to establish comparability. A shared metric name alone does not establish an identical protocol. ## Metrics - [GPT Accuracy](): Higher is better; unit: PERCENT. - [GPT Confidence](): Higher is better; unit: SCALAR. - [Human Accuracy](): Higher is better; unit: PERCENT. ## Recorded results | Method | GPT Accuracy | Result date | Report paper | | --- | --- | --- | --- | | UrbanKGent-13B | 52 | Not recorded | 68fa75111e209131cea657a1 | | UrbanKGent-8B | 47 | Not recorded | 68fa75111e209131cea657a1 | | UrbanKGent-7B | 46 | Not recorded | 68fa75111e209131cea657a1 | | GPT-4 | 45 | Not recorded | 68fa75111e209131cea657a1 | | GPT-3.5 | 43 | Not recorded | 68fa75111e209131cea657a1 | | GPT-3.5 | 41 | Not recorded | 68fa75111e209131cea657a1 | | GPT-4 | 38 | Not recorded | 68fa75111e209131cea657a1 | | Llama-2-13B | 35 | Not recorded | 68fa75111e209131cea657a1 | | Llama-3-70B | 35 | Not recorded | 68fa75111e209131cea657a1 | | Llama-2-70B | 33 | Not recorded | 68fa75111e209131cea657a1 | | Llama-2-7B | 32 | Not recorded | 68fa75111e209131cea657a1 | | Llama-3-8B | 31 | Not recorded | 68fa75111e209131cea657a1 | | Llama-2-13B | 31 | Not recorded | 68fa75111e209131cea657a1 | | GPT-3.5 | 29 | Not recorded | 68fa75111e209131cea657a1 | | Llama-3-8B | 29 | Not recorded | 68fa75111e209131cea657a1 | | Llama-2-7B | 27 | Not recorded | 68fa75111e209131cea657a1 | | Llama-2-13B | 26 | Not recorded | 68fa75111e209131cea657a1 | | Alpaca-7B | 26 | Not recorded | 68fa75111e209131cea657a1 | | Mistral-7B | 26 | Not recorded | 68fa75111e209131cea657a1 | | Llama-2-70B | 25 | Not recorded | 68fa75111e209131cea657a1 | | Llama-3-70B | 24 | Not recorded | 68fa75111e209131cea657a1 | | Vicuna-7B | 24 | Not recorded | 68fa75111e209131cea657a1 | | Llama-2-13B | 21 | Not recorded | 68fa75111e209131cea657a1 | | Llama-2-7B | 18 | Not recorded | 68fa75111e209131cea657a1 | | Llama-3-8B | 17 | Not recorded | 68fa75111e209131cea657a1 | | Llama-3-8B | 15 | Not recorded | 68fa75111e209131cea657a1 | | Mistral-7B | 14 | Not recorded | 68fa75111e209131cea657a1 | | Llama-2-7B | 14 | Not recorded | 68fa75111e209131cea657a1 | | RelationPrompt | 12 | Not recorded | 68fa75111e209131cea657a1 | | Vicuna-7B | 12 | Not recorded | 68fa75111e209131cea657a1 | | Alpaca-7B | 11 | Not recorded | 68fa75111e209131cea657a1 | | PRGC | 8 | Not recorded | 68fa75111e209131cea657a1 | ### UrbanKGent-13B GPT Accuracy: 52. Result ID: 69938b8a3a6c31484916bd60. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Type":"Agent"}. This record does not assert independent reproduction. ### UrbanKGent-8B GPT Accuracy: 47. Result ID: 69938b8a3a6c31484916bd5f. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Type":"Agent"}. This record does not assert independent reproduction. ### UrbanKGent-7B GPT Accuracy: 46. Result ID: 69938b8a3a6c31484916bd5e. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Type":"Agent"}. This record does not assert independent reproduction. ### GPT-4 GPT Accuracy: 45. Result ID: 69938b8a3a6c31484916bd5d. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Type":"UrbanKGent Inference"}. This record does not assert independent reproduction. ### GPT-3.5 GPT Accuracy: 43. Result ID: 69938b8a3a6c31484916bd5c. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Type":"UrbanKGent Inference"}. This record does not assert independent reproduction. ### GPT-3.5 GPT Accuracy: 41. Result ID: 69938b8a3a6c31484916bd50. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Type":"In-context Learning"}. This record does not assert independent reproduction. ### GPT-4 GPT Accuracy: 38. Result ID: 69938b8a3a6c31484916bd4c. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Type":"Zero-shot Reasoning"}. This record does not assert independent reproduction. ### Llama-2-13B GPT Accuracy: 35. Result ID: 69938b8a3a6c31484916bd53. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Type":"Vanilla Fine-tuning"}. This record does not assert independent reproduction. ### Llama-3-70B GPT Accuracy: 35. Result ID: 69938b8a3a6c31484916bd5b. [Reporting paper]() Recorded evaluation configuration: {"Type":"UrbanKGent Inference"}. This record does not assert independent reproduction. ### Llama-2-70B GPT Accuracy: 33. Result ID: 69938b8a3a6c31484916bd5a. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Type":"UrbanKGent Inference"}. This record does not assert independent reproduction. ### Llama-2-7B GPT Accuracy: 32. Result ID: 69938b8a3a6c31484916bd51. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Type":"Vanilla Fine-tuning"}. This record does not assert independent reproduction. ### Llama-3-8B GPT Accuracy: 31. Result ID: 69938b8a3a6c31484916bd52. [Reporting paper]() Recorded evaluation configuration: {"Type":"Vanilla Fine-tuning"}. This record does not assert independent reproduction. ### Llama-2-13B GPT Accuracy: 31. Result ID: 69938b8a3a6c31484916bd59. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Type":"UrbanKGent Inference"}. This record does not assert independent reproduction. ### GPT-3.5 GPT Accuracy: 29. Result ID: 69938b8a3a6c31484916bd4b. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Type":"Zero-shot Reasoning"}. This record does not assert independent reproduction. ### Llama-3-8B GPT Accuracy: 29. Result ID: 69938b8a3a6c31484916bd58. [Reporting paper]() Recorded evaluation configuration: {"Type":"UrbanKGent Inference"}. This record does not assert independent reproduction. ### Llama-2-7B GPT Accuracy: 27. Result ID: 69938b8a3a6c31484916bd57. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Type":"UrbanKGent Inference"}. This record does not assert independent reproduction. ### Llama-2-13B GPT Accuracy: 26. Result ID: 69938b8a3a6c31484916bd4f. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Type":"In-context Learning"}. This record does not assert independent reproduction. ### Alpaca-7B GPT Accuracy: 26. Result ID: 69938b8a3a6c31484916bd55. [Reporting paper]() Recorded evaluation configuration: {"Type":"UrbanKGent Inference"}. This record does not assert independent reproduction. ### Mistral-7B GPT Accuracy: 26. Result ID: 69938b8a3a6c31484916bd56. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Type":"UrbanKGent Inference"}. This record does not assert independent reproduction. ### Llama-2-70B GPT Accuracy: 25. Result ID: 69938b8a3a6c31484916bd49. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Type":"Zero-shot Reasoning"}. This record does not assert independent reproduction. ### Llama-3-70B GPT Accuracy: 24. Result ID: 69938b8a3a6c31484916bd4a. [Reporting paper]() Recorded evaluation configuration: {"Type":"Zero-shot Reasoning"}. This record does not assert independent reproduction. ### Vicuna-7B GPT Accuracy: 24. Result ID: 69938b8a3a6c31484916bd54. [Reporting paper]() Recorded evaluation configuration: {"Type":"UrbanKGent Inference"}. This record does not assert independent reproduction. ### Llama-2-13B GPT Accuracy: 21. Result ID: 69938b8a3a6c31484916bd48. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Type":"Zero-shot Reasoning"}. This record does not assert independent reproduction. ### Llama-2-7B GPT Accuracy: 18. Result ID: 69938b8a3a6c31484916bd4d. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Type":"In-context Learning"}. This record does not assert independent reproduction. ### Llama-3-8B GPT Accuracy: 17. Result ID: 69938b8a3a6c31484916bd4e. [Reporting paper]() Recorded evaluation configuration: {"Type":"In-context Learning"}. This record does not assert independent reproduction. ### Llama-3-8B GPT Accuracy: 15. Result ID: 69938b8a3a6c31484916bd47. [Reporting paper]() Recorded evaluation configuration: {"Type":"Zero-shot Reasoning"}. This record does not assert independent reproduction. ### Mistral-7B GPT Accuracy: 14. Result ID: 69938b8a3a6c31484916bd45. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Type":"Zero-shot Reasoning"}. This record does not assert independent reproduction. ### Llama-2-7B GPT Accuracy: 14. Result ID: 69938b8a3a6c31484916bd46. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Type":"Zero-shot Reasoning"}. This record does not assert independent reproduction. ### RelationPrompt GPT Accuracy: 12. Result ID: 69938b8a3a6c31484916bd41. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Type":"End-to-end Models"}. This record does not assert independent reproduction. ### Vicuna-7B GPT Accuracy: 12. Result ID: 69938b8a3a6c31484916bd43. [Reporting paper]() Recorded evaluation configuration: {"Type":"Zero-shot Reasoning"}. This record does not assert independent reproduction. ### Alpaca-7B GPT Accuracy: 11. Result ID: 69938b8a3a6c31484916bd44. [Reporting paper]() Recorded evaluation configuration: {"Type":"Zero-shot Reasoning"}. This record does not assert independent reproduction. ### PRGC GPT Accuracy: 8. Result ID: 69938b8a3a6c31484916bd42. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Type":"End-to-end Models"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.