Triple
T23111219
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Pink Slip |
E576324
|
entity |
| Predicate | hasOnscreenPerformance |
P79011
|
FINISHED |
| Object | school talent show |
—
|
LITERAL FINISHED |
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: school talent show | Statement: [Pink Slip, hasOnscreenPerformance, school talent show]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasOnscreenPerformance Context triple: [Pink Slip, hasOnscreenPerformance, school talent show]
-
A.
hasOnscreenFunction
Indicates that an entity serves a particular role or performs a specific function when it appears on screen.
-
B.
hasOnScreenDynamic
Indicates that one entity displays or presents another entity as a changing or interactive element on a screen.
-
C.
hasPerformanceElement
chosen
Indicates that one entity includes, contains, or is associated with a specific performance-related component or element.
-
D.
performedOnScreenBy
Indicates that an action, role, or performance is carried out by one entity in an on-screen context involving another entity.
-
E.
hasOffAxisPerformance
Indicates that an entity exhibits specific behavior or performance characteristics when observed or operated from an angle that is not aligned with its primary or intended axis.
- 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_69e245f4af548190898d434a64a1e774 |
completed | April 17, 2026, 2:38 p.m. |
| NER | Named-entity recognition | batch_69f18e0f4d188190a9395074c630ab0d |
completed | April 29, 2026, 4:50 a.m. |
| PD | Predicate disambiguation | batch_69ef89f020588190b43393e048e7eda3 |
completed | April 27, 2026, 4:08 p.m. |
Created at: April 17, 2026, 3:58 p.m.