Triple
T26354247
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | When the Morning Turns to Night |
E662986
|
entity |
| Predicate | hasOriginAlbum |
P102247
|
FINISHED |
| Object | Lukas Graham (Mama Said) |
—
|
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: Lukas Graham (Mama Said) | Statement: [When the Morning Turns to Night, hasOriginAlbum, Lukas Graham (Mama Said)]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasOriginAlbum Context triple: [When the Morning Turns to Night, hasOriginAlbum, Lukas Graham (Mama Said)]
-
A.
hasOriginalAlbumArtist
Indicates that an album is associated with the artist who is credited as its original primary creator or performer.
-
B.
includesOriginalAlbum
Indicates that one entity (such as a release, edition, or collection) fully contains or encompasses the complete content of another entity that is designated as the original album.
-
C.
hasAssociatedAlbum
chosen
Indicates that an entity is linked to a specific album with which it is related or connected.
-
D.
hasOriginalScoreAlbum
Indicates that an entity is associated with a specific album containing its original musical score.
-
E.
hasAlbumVersion
Indicates that one entity is an album-specific version or variant of another entity (such as a track, recording, or 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_69ee8130fc44819094e5ab1da201cd7b |
completed | April 26, 2026, 9:18 p.m. |
| NER | Named-entity recognition | batch_69f6db1f3ec48190a82e7d893d3c76ba |
completed | May 3, 2026, 5:20 a.m. |
| PD | Predicate disambiguation | batch_69f6d82adfa481908a5e196d2e18c73f |
completed | May 3, 2026, 5:07 a.m. |
Created at: April 26, 2026, 10:47 p.m.