Entity attribute ownership: six recorded examples
The downloads contain six original inputs, their expected labels and one recorded API observation per input revision. Disagreements stay visible.
Provide the note, target entity and proposed attribute. Compare supported ownership with a nearby entity's value, an unstated property or an ambiguous reference.
This example tests attribution rather than word matching. The same input can mention several devices or plans, and each attribute must stay attached to the correct entity.
The source post reports one contextual classification failure in a model comparison. This page uses new fictional device and subscription examples; it does not reproduce that comparison or rank models. Explicit relationship chains are allowed, while missing links stay Unstated.
This is an independently authored text demonstration inspired by the linked X discussion. Its rules and synthetic inputs are ours. It does not reproduce the source application, verify reported outcomes, or perform an external action.

Use the sample to understand the rule, then test your own input for entity attribute ownership.

Provide the note, target entity and proposed attribute.

Open the decision rules and keep the intended distinction between Supported, Contradicted, Unstated, Ambiguous. Edit the choices only when testing your own rule.

Use a sample first, then try your own input. Compare the selected label with the other returned probabilities.

Review Ambiguous before using a result. The label is a decision about the supplied information, not an executed action.
| Original input | Observed label | Leading probability |
|---|---|---|
| Assigned device | Supported | 100% |
| Nearby attribute | Contradicted | 100% |
| No assignment | Unstated | 97.0% |
| Unresolved person | Ambiguous | 78.0% |
| Direct property | Supported | 100% |
| Different property | Unstated | 98.0% |
These are six original synthetic inputs, tested once per request revision. The percentage is the leading option probability, not measured accuracy. Authored expectations and any disagreements remain in the downloadable evidence. 6 of 6 results matched the authored fixture expectations.Verified
The downloads contain six original inputs, their expected labels and one recorded API observation per input revision. Disagreements stay visible.
The single-request SDK runner uses your private TYPESAFE_API_KEY. The offline consumer reads saved observations, checks request hashes and prints a pending output. It does not call the model or change any external system.
# Offline: inspect the downloaded saved observations. No API key is needed.
python preview_choice_workflow.py samples.json saved-api-results.json
# Optional live request: install the SDK and set TYPESAFE_API_KEY privately.
npm install @typesafe-ai/sdk@0.6.0
node run-choice-sample.mjs samples.json case-1
# The live response prints to the terminal; it does not update saved-api-results.json.The input contract and these limits define what the result means.
No. The note must connect the property to the named target. A display type mentioned for another laptop does not establish the target laptop's display.
Unstated means the required relationship or property is missing. Contradicted requires an explicit incompatible value for that same property.
It describes the distribution over the supplied choices for this request. These six synthetic examples are functional tests with authored expectations, not a production accuracy benchmark.
No. The demo displays a label and distribution. The downloadable consumer produces a pending preview packet. Application code and a separate authorization policy would control any real action.
Edit the example above to see how a changed fact affects the decision, or open the Playground for another task.