Catalog lookup names: six recorded examples
The downloads contain six original inputs, their expected labels and one recorded API observation per input revision. Disagreements stay visible.
Give a lookup request and candidate text spans. Select the shortest complete work or person name, leaving ambiguous or incomplete candidates unmatched.
A search phrase and a catalog key serve different purposes. Director interviews belongs in a research query, but a film catalog may need only the film’s complete title. The requested lookup target must be explicit.
The model chooses from supplied strings. It does not check a catalog, disambiguate real people using hidden information or guarantee a match. Return None when the candidates omit the complete name.
This original text demonstration adapts a decision in a repository linked by the cited X post. The examples and explicit uncertainty outcomes are ours. The post is a directory reference, not proof that its author built every linked project. No third-party benchmark, business outcome or external action is reproduced.

Use the sample to understand the rule, then test your own input for catalog lookup names.

Give a lookup request and candidate text spans.

Open the decision rules and keep the intended distinction between A, B, C, None. 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 uncertain or unexpected results before using a result. The label is a decision about the supplied information, not an executed action.
| Original input | Observed label | Leading probability |
|---|---|---|
| Film title | A | 100% |
| Person name | B | 100% |
| Title contains common words | C | 100% |
| Broader question | B | 100% |
| Only fragments | None | 95.0% |
| Ambiguous target | None | 79.0% |
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.
Query selection retains topic relationships for a search. This task produces the complete entity-name candidate for a catalog that expects a name or title.
Not automatically. Preserve them when the input identifies them as part of the full title.
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.