Triple
T28434668
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Cloud 19 |
E715227
|
entity |
| Predicate | creditedAsBreakoutWorkFor |
P9650
|
FINISHED |
| Object | Kehlani |
—
|
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: Kehlani | Statement: [Cloud 19, creditedAsBreakoutWorkFor, Kehlani]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: creditedAsBreakoutWorkFor Context triple: [Cloud 19, creditedAsBreakoutWorkFor, Kehlani]
-
A.
breakthroughWorkOf
Indicates that one work is recognized as the major breakthrough or career-defining achievement of a particular creator or entity.
-
B.
gaveBreakthroughTo
Indicates that one entity provided another entity with a decisive insight, discovery, or advancement that significantly improved their progress or understanding.
-
C.
breakthroughAlbum
chosen
Indicates that an album represents a major artistic or commercial turning point that significantly elevates an artist’s recognition or success.
-
D.
breakthroughBy
Indicates that a significant discovery, innovation, or advance was achieved or brought about by a particular agent or entity.
-
E.
isOneOfMostSuccessfulWorksOf
Indicates that one entity is among the most successful works or creations associated with 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_69efd6b253888190b3c7222ed6a403a8 |
completed | April 27, 2026, 9:35 p.m. |
| NER | Named-entity recognition | batch_69f64e391974819085b2c505fdb804f3 |
completed | May 2, 2026, 7:19 p.m. |
| PD | Predicate disambiguation | batch_69f64caede108190a35cc7cbfead866f |
completed | May 2, 2026, 7:12 p.m. |
Created at: April 28, 2026, 1:42 a.m.