Triple
T22766663
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Old Folks at Home |
E563143
|
entity |
| Predicate | lyricsRevisedToRemove |
P14953
|
FINISHED |
| Object | racially offensive language |
—
|
LITERAL 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: racially offensive language | Statement: [Old Folks at Home, lyricsRevisedToRemove, racially offensive language]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: lyricsRevisedToRemove Context triple: [Old Folks at Home, lyricsRevisedToRemove, racially offensive language]
-
A.
modifiedLyricsDetail
chosen
Indicates that the relationship specifies detailed information about how the original lyrics have been altered or modified.
-
B.
lyricsOfficiallyUsedUntil
Indicates the date or time period up to which specific lyrics were officially in use or recognized as valid.
-
C.
lyricSetting
Indicates that one entity serves as the text or lyrics that are set to music or otherwise musically realized by another entity.
-
D.
lyricText
Indicates that one entity is the lyrical content or words of a song or musical piece associated with another entity.
-
E.
lyricReference
Indicates that one entity (typically a work or text) contains or makes a reference to the lyrics of another entity.
- 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_69e24552e11c81909c2d61578a558bd7 |
completed | April 17, 2026, 2:36 p.m. |
| NER | Named-entity recognition | batch_69f17a80e2688190b76844c408929d32 |
completed | April 29, 2026, 3:26 a.m. |
| PD | Predicate disambiguation | batch_69eed2b88d88819096015deb6a648801 |
completed | April 27, 2026, 3:06 a.m. |
Created at: April 17, 2026, 3:26 p.m.