Triple
T15603709
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Etan Cohen |
E375098
|
entity |
| Predicate | wrote |
P2831
|
FINISHED |
| Object | Get Hard |
E255779
|
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: Get Hard | Statement: [Etan Cohen, wrote, Get Hard]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Get Hard Context triple: [Etan Cohen, wrote, Get Hard]
-
A.
Get Hard
chosen
Get Hard is a 2015 American comedy film starring Will Ferrell and Kevin Hart, centered on a wealthy businessman preparing for prison with the help of a small-time car washer.
-
B.
Go Hard
"Go Hard" is a track by Nicki Minaj featured on her mixtape *Beam Me Up Scotty*, showcasing her aggressive flow and punchline-heavy rap style.
-
C.
So Hard
"So Hard" is a 1990 synth-pop single by the English duo Pet Shop Boys, known for its bittersweet lyrics about a troubled relationship and its dance-oriented production.
-
D.
Hard-Off
Hard-Off is a studio album by the American comedy rock band Bloodhound Gang, known for its irreverent humor and provocative lyrics.
-
E.
Hit This Hard
"Hit This Hard" is a song by American rapper Post Malone from his debut studio album "Stoney."
- 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_69d85cce25008190b13b52745fbd719b |
completed | April 10, 2026, 2:13 a.m. |
| NER | Named-entity recognition | batch_69e04e6399d88190b2c3e781667666d4 |
completed | April 16, 2026, 2:50 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ff5f37383c81909d0efce84508a034 |
completed | May 9, 2026, 4:22 p.m. |
Created at: April 10, 2026, 4:12 a.m.