Triple
T21425007
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Greeny |
E528529
|
entity |
| Predicate | notableRecording |
P1152
|
FINISHED |
| Object | “Oh Well” |
—
|
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: “Oh Well” | Statement: [Greeny, notableRecording, “Oh Well”]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: “Oh Well” Context triple: [Greeny, notableRecording, “Oh Well”]
-
A.
Oh Well
chosen
"Oh Well" is a 1969 blues-rock song by Fleetwood Mac, written by guitarist Peter Green and known for its distinctive riff and two-part structure.
-
B.
“Oh Lord”
“Oh Lord” is an R&B/gospel-influenced song by Brian McKnight featured on his self-titled debut album.
-
C.
You Wear It Well
"You Wear It Well" is an R&B song by the American family group DeBarge, known for its smooth vocals and romantic, soulful style.
-
D.
You Wear It Well
"You Wear It Well" is a 1972 folk-rock song by Rod Stewart, known for its storytelling lyrics and success as a hit single from his album "Never a Dull Moment."
-
E.
Sittin’ on Top of the World
"Sittin’ on Top of the World" is a hit song by Nigerian artist Burna Boy that blends Afrobeats with contemporary pop and hip-hop influences.
- 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_69e0c455f3688190810bc96365791b0f |
completed | April 16, 2026, 11:13 a.m. |
| NER | Named-entity recognition | batch_69ee813c7a048190a400e364c8df1dcf |
completed | April 26, 2026, 9:18 p.m. |
Created at: April 16, 2026, 5:48 p.m.