Triple
T21438459
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Bill Withers |
E528875
|
entity |
| Predicate | notableWork |
P4
|
FINISHED |
| Object | Lean on Me |
—
|
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: Lean on Me | Statement: [Bill Withers, notableWork, Lean on Me]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Lean on Me Context triple: [Bill Withers, notableWork, Lean on Me]
-
A.
Lean on Me
"Lean on Me" is a Grammy-winning contemporary gospel and R&B song by Kirk Franklin featuring an ensemble of prominent vocalists, known for its uplifting message of support and faith.
-
B.
Lean on Me
chosen
"Lean on Me" is a 1989 American drama film starring Morgan Freeman as a tough, unconventional high school principal working to reform a troubled inner-city school.
-
C.
I'll Stand by You
"I'll Stand by You" is a pop rock ballad originally recorded by The Pretenders that has been widely covered and featured in various television shows and compilations.
-
D.
It Don’t Matter to Me
"It Don’t Matter to Me" is a song by Phil Collins featured on his 1982 solo album "Hello, I Must Be Going!".
-
E.
More Than I Can Say
"More Than I Can Say" is a popular pop ballad best known for its hit recordings by Bobby Vee in 1961 and later by Leo Sayer in 1980.
- 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_69e0c4569fa081908101baa24f8745db |
completed | April 16, 2026, 11:13 a.m. |
| NER | Named-entity recognition | batch_69ee8140a1fc8190bedf297cfc4d4841 |
completed | April 26, 2026, 9:18 p.m. |
Created at: April 16, 2026, 6:04 p.m.