Triple
T22655623
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Crazy for You |
E559217
|
entity |
| Predicate | featuresSong |
P2152
|
FINISHED |
| Object | Things Are Looking Up |
—
|
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: Things Are Looking Up | Statement: [Crazy for You, featuresSong, Things Are Looking Up]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Things Are Looking Up Context triple: [Crazy for You, featuresSong, Things Are Looking Up]
-
A.
Things Are Looking Up
"Things Are Looking Up" is a track by American producer and DJ RJD2, known for his sample-rich, genre-blending instrumental hip-hop style.
-
B.
Things Are Looking Up
chosen
"Things Are Looking Up" is a popular song by George and Ira Gershwin, introduced by Fred Astaire in the 1937 film musical *A Damsel in Distress*.
-
C.
Going Up
"Going Up" is a song featured on the Christian worship album "Side by Side."
-
D.
Ever Upward
Ever Upward is the official English motto of the U.S. state of New York, expressing a spirit of continual progress and aspiration.
-
E.
Get Up on It
"Get Up on It" is an R&B album by American singer Keith Sweat, known for its smooth slow jams and new jack swing-influenced production from the mid-1990s.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69e245489dd88190b1f674acf61c8769 |
completed | April 17, 2026, 2:35 p.m. |
| NER | Named-entity recognition | batch_69f1765b93dc8190a0357dd4b6ae524a |
completed | April 29, 2026, 3:09 a.m. |
Created at: April 17, 2026, 3:06 p.m.