# Sentential Relation Extraction on Human Annotation Dataset Wikidata (test)

Source: [Sentential Relation Extraction on Human Annotation Dataset Wikidata (test)](<https://www.sota2.com/research/sota/sentential-relation-extraction-on-human-annotation-dataset-wikidata-test>)

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

Data updated: 2026-02-26T05:52:45.231Z

Evaluation of Sentential Relation Extraction performance on the test split of the Human Annotation Dataset Wikidata, measured using Micro Precision, Recall, and F1 scores.

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 | Sentential Relation Extraction |
| Dataset (including any stated split) | Human Annotation Dataset Wikidata (test) |
| Metric | Micro Precision |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 6 of 6 |
| 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

- [Micro Precision](<https://www.sota2.com/research/sota/sentential-relation-extraction-on-human-annotation-dataset-wikidata-test.md?metric=Micro%20Precision>): Higher is better; unit: PERCENT.

- [Micro Recall](<https://www.sota2.com/research/sota/sentential-relation-extraction-on-human-annotation-dataset-wikidata-test.md?metric=Micro%20Recall>): Higher is better; unit: PERCENT.

- [Micro F1](<https://www.sota2.com/research/sota/sentential-relation-extraction-on-human-annotation-dataset-wikidata-test.md?metric=Micro%20F1>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Micro Precision | Result date | Report paper |
| --- | --- | --- | --- |
| KGPool+gnn | 89.36 | Not recorded | 68fa6a221e209131cea26371 |
| RECON | 87.34 | Not recorded | 68fa6a221e209131cea26371 |
| KGPool+lstm | 86.34 | Not recorded | 68fa6a221e209131cea26371 |
| RECON-EAC | 86.1 | Not recorded | 68fa6a221e209131cea26371 |
| GP-GNN | 81.99 | Not recorded | 68fa6a221e209131cea26371 |
| Context Aware LSTM | 77.77 | Not recorded | 68fa6a221e209131cea26371 |

### KGPool+gnn

Micro Precision: 89.36. Result ID: 698e13e1ffc3901de09aa25c.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6a221e209131cea26371.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6a221e209131cea26371.md>)

[Implementation](<https://github.com/nadgeri14/KGPool>)

Recorded evaluation configuration: {"alpha":"1"}. This record does not assert independent reproduction.

### RECON

Micro Precision: 87.34. Result ID: 698e13e1ffc3901de09aa25a.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6a221e209131cea26371.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa69191e209131cea20386.md>)

[Implementation](<https://github.com/ansonb/RECON>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### KGPool+lstm

Micro Precision: 86.34. Result ID: 698e13e1ffc3901de09aa25b.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6a221e209131cea26371.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6a221e209131cea26371.md>)

[Implementation](<https://github.com/nadgeri14/KGPool>)

Recorded evaluation configuration: {"alpha":"1"}. This record does not assert independent reproduction.

### RECON-EAC

Micro Precision: 86.1. Result ID: 698e13e1ffc3901de09aa259.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6a221e209131cea26371.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa69191e209131cea20386.md>)

[Implementation](<https://github.com/ansonb/RECON>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### GP-GNN

Micro Precision: 81.99. Result ID: 698e13e1ffc3901de09aa258.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6a221e209131cea26371.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa65551e209131cea09ca0.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### Context Aware LSTM

Micro Precision: 77.77. Result ID: 698e13e1ffc3901de09aa257.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6a221e209131cea26371.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

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