Triple
T25033283
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Brook Benton |
E626907
|
entity |
| Predicate | songwritingForOthers |
P157915
|
FINISHED |
| Object | wrote songs for Clyde McPhatter |
—
|
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: wrote songs for Clyde McPhatter | Statement: [Brook Benton, songwritingForOthers, wrote songs for Clyde McPhatter]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: songwritingForOthers Context triple: [Brook Benton, songwritingForOthers, wrote songs for Clyde McPhatter]
-
A.
songwritingForOthers
chosen
Indicates that an entity creates songs intended to be performed or used by other entities rather than themselves.
-
B.
coSongwriter
Indicates that two or more entities collaborated in writing the same song.
-
C.
songwriterCollective
Indicates a relationship where a songwriter is a member of, or affiliated with, a collective group of songwriters.
-
D.
songwritingTheme
Indicates that one entity serves as the thematic subject or central topic of another entity’s songwriting.
-
E.
writesLyricsIn
Indicates that an entity creates or composes song lyrics in a specified language or writing system.
- F. None of above.
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_69e2ff2a2c088190be513727ee8bfe78 |
completed | April 18, 2026, 3:48 a.m. |
| NER | Named-entity recognition | batch_69f464b4c9b0819085daa00c7c3b8b76 |
completed | May 1, 2026, 8:30 a.m. |
| PD | Predicate disambiguation | batch_69f45cfb53f4819099bba48c5057e787 |
completed | May 1, 2026, 7:57 a.m. |
Created at: April 18, 2026, 6:07 a.m.