Triple
T25919077
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Break Up with Your Girlfriend, I'm Bored |
E653116
|
entity |
| Predicate | interpolatedWorkArtist |
P112080
|
FINISHED |
| Object | NSYNC |
—
|
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: NSYNC | Statement: [Break Up with Your Girlfriend, I'm Bored, interpolatedWorkArtist, NSYNC]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: interpolatedWorkArtist Context triple: [Break Up with Your Girlfriend, I'm Bored, interpolatedWorkArtist, NSYNC]
-
A.
worksWithArtist
Indicates that one entity collaborates or engages in professional work with an artist.
-
B.
artistOf
Indicates that one entity is the creator or performer responsible for producing a particular work or piece.
-
C.
producerArtist
Indicates that one entity serves as the producer (e.g., overseeing or managing the creation) of a work created or performed by the artist entity.
-
D.
originalSongwritersOfInterpolatedWork
chosen
Indicates that the linked entities are the original songwriters whose work has been interpolated into another musical composition.
-
E.
backedArtist
Indicates that one entity has provided support, endorsement, or resources to an artist 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_69e7ab3e025c819086771607157f0015 |
completed | April 21, 2026, 4:52 p.m. |
| NER | Named-entity recognition | batch_69f6691f5e188190b12c7b2eb729a45e |
completed | May 2, 2026, 9:14 p.m. |
| PD | Predicate disambiguation | batch_69f66598d6008190a7ca8ff80399fd34 |
completed | May 2, 2026, 8:59 p.m. |
Created at: April 22, 2026, 8:31 a.m.