Triple
T30427334
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | The Best of Brandy |
E774068
|
entity |
| Predicate | compilesSinglesFrom |
P154427
|
FINISHED |
| Object | Brandy |
—
|
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: Brandy | Statement: [The Best of Brandy, compilesSinglesFrom, Brandy]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: compilesSinglesFrom Context triple: [The Best of Brandy, compilesSinglesFrom, Brandy]
-
A.
includesSinglesFrom
chosen
Indicates that a collection or group contains individual single items originating from a specified source or set.
-
B.
isCompilationOf
Indicates that one entity is a collected or assembled version made up of multiple other entities.
-
C.
compilesPreviouslyReleasedSongs
Indicates that an entity assembles or collects songs that were previously released into a new compilation or collection.
-
D.
numberOfSingles
Indicates the count of individual single items (such as single tracks, units, or occurrences) associated with a given entity.
-
E.
compilesWorkOf
Indicates that one entity gathers, edits, or assembles the works created by another entity into a collection or compilation.
- 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_69f22491ba248190b9a4776ca8e42d02 |
completed | April 29, 2026, 3:32 p.m. |
| NER | Named-entity recognition | batch_69f6866990548190aea96f3a46ba2e43 |
completed | May 2, 2026, 11:19 p.m. |
| PD | Predicate disambiguation | batch_69f678d2196c8190b9d0d2fcd47cc539 |
completed | May 2, 2026, 10:21 p.m. |
Created at: April 29, 2026, 8:06 p.m.