Triple
T9741063
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Punk'd |
E236184
|
entity |
| Predicate | originallyTargetedMedium |
P56966
|
FINISHED |
| Object | television |
—
|
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: television | Statement: [Punk'd, originallyTargetedMedium, television]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: originallyTargetedMedium Context triple: [Punk'd, originallyTargetedMedium, television]
-
A.
targetMedium
chosen
Indicates the medium or channel through which an action, message, or effect is directed or intended to be delivered.
-
B.
primaryMedium
Indicates the main material, format, or channel through which something is created, expressed, or communicated.
-
C.
intendedTargets
Indicates that an action, message, or object is specifically directed toward or meant to affect particular target entities.
-
D.
primaryTarget
Indicates that an entity is the main or most important target of another entity’s action, focus, or effect.
-
E.
targetedBecauseOf
Indicates that one entity is made a target of an action, harm, or scrutiny specifically due to possessing a particular attribute, identity, or characteristic.
- 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_69ca84d3e24481908a476e2231123cf9 |
completed | March 30, 2026, 2:12 p.m. |
| NER | Named-entity recognition | batch_69cd9f2af3e48190b83a442cd0e84062 |
completed | April 1, 2026, 10:41 p.m. |
| PD | Predicate disambiguation | batch_69cd03cc128c81908b84ef224f858b4e |
completed | April 1, 2026, 11:38 a.m. |
Created at: March 30, 2026, 8:23 p.m.