Word-game entry forms: 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 entry and its construction facts. Distinguish a sentence, ordinary-word compound and coined token without claiming the token is globally new.
This is an English adaptation of a Japanese word-game idea. The source game uses additional judgments about knownness and readings; this page demonstrates only the form distinction.
Coined token describes the supplied construction, not the absence of that spelling from every language, dictionary, product or name. Verify novelty separately if a game or naming project requires it.
Construction facts help explain why an entry counts as a compound. Do not manufacture a word's etymology simply because two familiar-looking fragments appear in it.
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 author’s application, verify reported outcomes, or perform an external action.

Use the sample to understand the rule, then test your own input for word-game entry forms.

Provide the entry and its construction facts.

Open the decision rules and keep the intended distinction between Sentence, Compound, Coined token, Review. 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 Review before using a result. The label is a decision about the supplied information, not an executed action.
| Original input | Observed label | Leading probability |
|---|---|---|
| Complete utterance | Sentence | 100% |
| Transparent combination | Compound | 100% |
| Original token | Coined token | 99.0% |
| Another compound | Compound | 100% |
| Contradictory facts | Review | 97.0% |
| No language context | Review | 84.0% |
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. It means the input describes a single invented-form token under this game rule. The model has not searched every dictionary or name registry.
No. Its source is a Japanese game, while these original examples and rules are in English. It does not implement the source's readings, dictionary fallback or multiplayer interface.
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.