Triple
T20876019
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | I'm Only Sleeping |
E514018
|
entity |
| Predicate | mixVariations |
P130790
|
FINISHED |
| Object | different US and UK mixes |
—
|
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: different US and UK mixes | Statement: [I'm Only Sleeping, mixVariations, different US and UK mixes]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: mixVariations Context triple: [I'm Only Sleeping, mixVariations, different US and UK mixes]
-
A.
mixType
chosen
Indicates that one entity is combined or blended with another in a particular manner or category of mixing.
-
B.
mixesElementsOf
Indicates a relationship where one entity combines or blends components, features, or aspects of another entity or set of entities into a unified whole.
-
C.
mixesElement
Indicates that one entity combines or blends another entity or element into a mixture or composite.
-
D.
mixingMethod
Indicates the technique or process used to combine multiple components or substances into a uniform mixture.
-
E.
mixedAt
Indicates that one entity has been combined or blended together with another entity (or entities), typically to form a mixture at a specific time or place.
- 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_69e0b4f675cc8190b4e745225b62eb66 |
completed | April 16, 2026, 10:07 a.m. |
| NER | Named-entity recognition | batch_69e6c674f68c8190a7b43aeea5b9b976 |
completed | April 21, 2026, 12:36 a.m. |
| PD | Predicate disambiguation | batch_69e5c9a8dc148190b33ff51894e2a8f9 |
completed | April 20, 2026, 6:37 a.m. |
Created at: April 16, 2026, 12:45 p.m.