Triple
T22390150
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Back Home |
E553490
|
entity |
| Predicate | basedOnSongBy |
P70238
|
FINISHED |
| Object | Michael Bublé |
—
|
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: Michael Bublé | Statement: [Back Home, basedOnSongBy, Michael Bublé]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Michael Bublé Context triple: [Back Home, basedOnSongBy, Michael Bublé]
-
A.
Michael Bublé
chosen
Michael Bublé is a Canadian singer and songwriter renowned for his smooth vocals and modern interpretations of traditional pop and jazz standards.
-
B.
Josh Groban
Josh Groban is an American singer, songwriter, and actor known for his powerful baritone voice and crossover classical-pop ballads.
-
C.
Julian Bunetta
Julian Bunetta is an American songwriter and record producer known for his work with major pop artists such as One Direction and Meghan Trainor.
-
D.
Eric Benét
Eric Benét is an American R&B and neo-soul singer, songwriter, and actor known for his smooth vocals and romantic ballads.
-
E.
Dave Koz
Dave Koz is an American smooth jazz saxophonist and composer known for his melodic style, numerous chart-topping albums, and collaborations across the contemporary jazz and pop scenes.
- 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_69e11e4cf87c8190a1ff474daec326b7 |
completed | April 16, 2026, 5:37 p.m. |
| NER | Named-entity recognition | batch_69f15859853c8190b849cb34a94106da |
completed | April 29, 2026, 1:01 a.m. |
Created at: April 16, 2026, 8:45 p.m.