Triple
T25831910
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | "Say goodnight, Gracie" closing routine |
E650685
|
entity |
| Predicate | promptText |
P66120
|
FINISHED |
| Object | Say goodnight, Gracie |
—
|
NE NERFINISHED |
How this triple was built (2 steps)
Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.
NER
Named-entity recognition
gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: Say goodnight, Gracie | Statement: ["Say goodnight, Gracie" closing routine, promptText, Say goodnight, Gracie]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: promptText Context triple: ["Say goodnight, Gracie" closing routine, promptText, Say goodnight, Gracie]
-
A.
promptType
Indicates the specific category or style of a prompt that characterizes how an instruction or request is framed or intended to be interpreted.
-
B.
promptedAction
Indicates that one entity initiates or triggers another entity to perform a specific action.
-
C.
pretext
Indicates that one party uses a stated reason or excuse to conceal their true motive for an action or decision.
-
D.
questionText
Indicates the textual content of a question as it is posed or displayed.
-
E.
primaryTextUsed
chosen
Indicates that a particular text is the main or principal textual content used in relation to another entity or resource.
- F. None of above.
Provenance (3 batches)
The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.
| Step | Stage | Batch ID | Status | When |
|---|---|---|---|---|
| creating | Elicitation | batch_69e7ab37438081908f1ccf6284839520 |
completed | April 21, 2026, 4:52 p.m. |
| NER | Named-entity recognition | batch_69f601f26f0c81908f0ee76b955e9806 |
completed | May 2, 2026, 1:53 p.m. |
| PD | Predicate disambiguation | batch_69f4938b960081909b53c074a3e0c7c2 |
completed | May 1, 2026, 11:50 a.m. |
Created at: April 22, 2026, 7:39 a.m.