**The most important numeric metric is `petal_length`.** This is a judgement call, because the dataset has no single "value" column. I chose it because it separates the three species best, which is the main decision this data serves. **Why petal_length** - Species averages are far apart: setosa 1.46, versicolor 4.26, virginica 5.55 (gold table `iris_by_species`). - Setosa is fully separated. Its maximum petal length is 1.9, while the lowest of any other species is 3.0 (versicolor). - Versicolor and virginica overlap only slightly, between 4.5 and 5.1. - The sepal measures are weaker separators. Sepal width ranges overlap heavily across species: setosa 2.3–4.4, versicolor 2.0–3.4, virginica 2.2–3.8. - Petal width is similarly strong (averages 0.25, 1.33, 2.03), but petal length has the wider spread between species. **Highest and lowest records** (query on `raw.iris` by `petal_length`, step 2) - **Highest:** a *virginica* specimen with petal_length 6.9, petal_width 2.3, sepal_length 7.7 and sepal_width 2.6. - **Lowest:** a *setosa* specimen with petal_length 1.0, petal_width 0.2, sepal_length 4.6 and sepal_width 3.6. These match the per-species minimum and maximum in the gold table, where setosa has a minimum of 1.0 and virginica a maximum of 6.9. The query returned one record per extreme, so other specimens may share those exact values. The two extremes come from the smallest-petalled and largest-petalled species. Petal length alone therefore spans the full range of the data, from 1.0 to 6.9, and covers all three species.