# Relational Triplet Extraction on NYC-Large (test)

Source: [Relational Triplet Extraction on NYC-Large (test)](<https://www.sota2.com/research/sota/relational-triplet-extraction-on-nyc-large-test>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-02-26T05:45:45.254Z

Evaluation of Relational Triplet Extraction performance on the test split of the NYC-Large 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 |
| Dataset (including any stated split) | NYC-Large (test) |
| Metric | GPT Accuracy |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 7 of 7 |
| 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](<https://www.sota2.com/research/sota/relational-triplet-extraction-on-nyc-large-test.md?metric=GPT%20Accuracy>): Higher is better; unit: PERCENT.

- [GPT Confidence](<https://www.sota2.com/research/sota/relational-triplet-extraction-on-nyc-large-test.md?metric=GPT%20Confidence>): Higher is better; unit: SCALAR.

- [Human Accuracy](<https://www.sota2.com/research/sota/relational-triplet-extraction-on-nyc-large-test.md?metric=Human%20Accuracy>): Higher is better; unit: PERCENT.

## Recorded results

| Method | GPT Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| UrbanKGent-13B | 46 | Not recorded | 68fa75111e209131cea657a1 |
| UrbanKGent-7B | 44 | Not recorded | 68fa75111e209131cea657a1 |
| UrbanKGent Inference | 43 | Not recorded | 68fa75111e209131cea657a1 |
| UrbanKGent-8B | 43 | Not recorded | 68fa75111e209131cea657a1 |
| ICL | 39 | Not recorded | 68fa75111e209131cea657a1 |
| VFT | 37 | Not recorded | 68fa75111e209131cea657a1 |
| ZSL | 36 | Not recorded | 68fa75111e209131cea657a1 |

### UrbanKGent-13B

GPT Accuracy: 46. Result ID: 69938b8a3a6c31484916bd2b.

[Reporting paper](<https://www.sota2.com/research/paper/68fa75111e209131cea657a1.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa75111e209131cea657a1.md>)

[Implementation](<https://github.com/usail-hkust/UrbanKGent>)

Recorded evaluation configuration: {"Model Scale":"13B"}. This record does not assert independent reproduction.

### UrbanKGent-7B

GPT Accuracy: 44. Result ID: 69938b8a3a6c31484916bd29.

[Reporting paper](<https://www.sota2.com/research/paper/68fa75111e209131cea657a1.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa75111e209131cea657a1.md>)

[Implementation](<https://github.com/usail-hkust/UrbanKGent>)

Recorded evaluation configuration: {"Model Scale":"7B"}. This record does not assert independent reproduction.

### UrbanKGent Inference

GPT Accuracy: 43. Result ID: 69938b8a3a6c31484916bd28.

[Reporting paper](<https://www.sota2.com/research/paper/68fa75111e209131cea657a1.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa75111e209131cea657a1.md>)

[Implementation](<https://github.com/usail-hkust/UrbanKGent>)

Recorded evaluation configuration: {"Mode":"Inference setting"}. This record does not assert independent reproduction.

### UrbanKGent-8B

GPT Accuracy: 43. Result ID: 69938b8a3a6c31484916bd2a.

[Reporting paper](<https://www.sota2.com/research/paper/68fa75111e209131cea657a1.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa75111e209131cea657a1.md>)

[Implementation](<https://github.com/usail-hkust/UrbanKGent>)

Recorded evaluation configuration: {"Model Scale":"8B"}. This record does not assert independent reproduction.

### ICL

GPT Accuracy: 39. Result ID: 69938b8a3a6c31484916bd26.

[Reporting paper](<https://www.sota2.com/research/paper/68fa75111e209131cea657a1.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6e571e209131cea3f27b.md>)

Recorded evaluation configuration: {"Learning Paradigm":"In-context-learning"}. This record does not assert independent reproduction.

### VFT

GPT Accuracy: 37. Result ID: 69938b8a3a6c31484916bd27.

[Reporting paper](<https://www.sota2.com/research/paper/68fa75111e209131cea657a1.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa76f41e209131cea7037b.md>)

Recorded evaluation configuration: {"Learning Paradigm":"Vanilla Fine-tuning"}. This record does not assert independent reproduction.

### ZSL

GPT Accuracy: 36. Result ID: 69938b8a3a6c31484916bd25.

[Reporting paper](<https://www.sota2.com/research/paper/68fa75111e209131cea657a1.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa70f21e209131cea4e458.md>)

[Implementation](<https://github.com/wangcunxiang/QA-Eval>)

Recorded evaluation configuration: {"Learning Paradigm":"Zero-shot-learning"}. This record does not assert independent reproduction.

Page 1 of 1. This is an index page, not the full collection.