Triple
T2473369
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | The Jackson 5 |
E55026
|
entity |
| Predicate | breakthroughSingle |
P3283
|
FINISHED |
| Object | I Want You Back |
E270817
|
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: I Want You Back | Statement: [The Jackson 5, breakthroughSingle, I Want You Back]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: I Want You Back Context triple: [The Jackson 5, breakthroughSingle, I Want You Back]
-
A.
I Want You Back
chosen
"I Want You Back" is a 1969 Motown hit single by the Jackson 5 that became one of their signature songs and a classic of pop and soul music.
-
B.
I Want You
"I Want You" is a fast-paced, lyrically intricate love song by Bob Dylan, featured on his 1966 album Blonde on Blonde.
-
C.
I Want You
"I Want You" is a soulful hip-hop track by Common, produced by will.i.am, known for its smooth, romantic vibe and lush, sample-based instrumentation.
-
D.
Could You Be Loved
"Could You Be Loved" is a popular reggae song by Bob Marley and the Wailers, known for its upbeat groove and message of love and resilience.
-
E.
I Want to Be with You
"I Want to Be with You" is a soul/R&B song popularized by American singer Dee Dee Warwick in the 1960s.
- 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_69ab49e279e88190ab10d7248aea9d11 |
completed | March 6, 2026, 9:40 p.m. |
| NER | Named-entity recognition | batch_69abd149c10c819098ff75f176972c8b |
completed | March 7, 2026, 7:18 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69af1f8990488190bc54cc5eadf11baa |
completed | March 9, 2026, 7:29 p.m. |
Created at: March 6, 2026, 9:45 p.m.