Triple
T13994686
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Saturday Night Live digital shorts |
E336663
|
entity |
| Predicate | notableWork |
P4
|
FINISHED |
| Object | Jizz in My Pants |
E336655
|
NE 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: Jizz in My Pants | Statement: [Saturday Night Live digital shorts, notableWork, Jizz in My Pants]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Jizz in My Pants Context triple: [Saturday Night Live digital shorts, notableWork, Jizz in My Pants]
-
A.
Jizz in My Pants
chosen
"Jizz in My Pants" is a comedic electropop song and digital short by The Lonely Island that parodies melodramatic dance-pop and premature ejaculation.
-
B.
Dirty Pants
"Dirty Pants" is a song featured on the album "Rain on Lens" by the indie rock band Smog (Bill Callahan).
-
C.
Teach Me How to Jerk
"Teach Me How to Jerk" is a hip hop dance track by Audio Push that helped popularize the jerkin' dance movement in the late 2000s.
-
D.
Niggy Nuts
Niggy Nuts is a component or member associated with the entity referred to as the "G.O.A.T." (Greatest of All Time).
-
E.
Punch You in the Jeans
"Punch You in the Jeans" is a comedic rap song by The Lonely Island, featured on their debut studio album *Incredibad*.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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_69d81c645c5c8190b1fd16a285a1b78a |
completed | April 9, 2026, 9:38 p.m. |
| NER | Named-entity recognition | batch_69de2eb53f508190855cd69b8061dd77 |
completed | April 14, 2026, 12:10 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69fbc32789e08190be0f1d1685dcc90e |
completed | May 6, 2026, 10:39 p.m. |
Created at: April 9, 2026, 10:19 p.m.