Triple
T22821398
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mama Do (Uh Oh, Uh Oh) |
E565237
|
entity |
| Predicate | hasBside |
P15273
|
FINISHED |
| Object | Want You |
—
|
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: Want You | Statement: [Mama Do (Uh Oh, Uh Oh), hasBside, Want You]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Want You Context triple: [Mama Do (Uh Oh, Uh Oh), hasBside, Want You]
-
A.
Want You
chosen
"Want You" is a song featured on Mariah Carey's 2001 soundtrack album *Glitter*.
-
B.
Want You Back
"Want You Back" is a pop-rock single by Australian band 5 Seconds of Summer, released in 2018 as the lead track from their third studio album "Youngblood."
-
C.
Want You Back
"Want You Back" is a 2017 pop-rock single by the American band Haim, known for its catchy hooks and polished, harmony-driven production.
-
D.
If You Want Me
"If You Want Me" is a country song recorded by American singer Billie Jo Spears, known for its classic 1970s Nashville sound and Spears’ emotive vocal style.
-
E.
If You Want Me
"If You Want Me" is an R&B song by the American girl group Kima, Keisha & Pam, known from the platinum-selling group Total.
- 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_69e2458426188190b58b8ab4844fe420 |
completed | April 17, 2026, 2:36 p.m. |
| NER | Named-entity recognition | batch_69f17dcffdd88190a5f9c780c71b5053 |
completed | April 29, 2026, 3:41 a.m. |
Created at: April 17, 2026, 3:33 p.m.