Triple
T20268108
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Cheating on You |
E499019
|
entity |
| Predicate | hasCoverArtText |
P15271
|
FINISHED |
| Object | “This song is not about a person” |
—
|
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: “This song is not about a person” | Statement: [Cheating on You, hasCoverArtText, “This song is not about a person”]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasCoverArtText Context triple: [Cheating on You, hasCoverArtText, “This song is not about a person”]
-
A.
hasCoverArtFeaturing
Indicates that one entity’s cover art visually features or depicts another entity.
-
B.
hasCoverArtSource
Indicates that an entity’s cover art is derived from, or visually based on, another specified source entity.
-
C.
hasCoverArtVariant
Indicates that an item has an alternative version of its cover artwork distinct from the primary cover.
-
D.
hasCoverArtTheme
Indicates that an item’s cover art visually represents or is characterized by a particular theme or motif.
-
E.
coverArtText
chosen
Indicates that the text element is part of, or associated with, the cover art of a work.
- 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_69da6275fa6c8190952924930adee150 |
completed | April 11, 2026, 3:02 p.m. |
| NER | Named-entity recognition | batch_69e675dbb7ac8190a40c527f2c02ca50 |
completed | April 20, 2026, 6:52 p.m. |
| PD | Predicate disambiguation | batch_69e55b1e5e1c8190ba8a5544b1db9e1d |
completed | April 19, 2026, 10:45 p.m. |
Created at: April 11, 2026, 11:42 p.m.