Triple
T31315816
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Run (Taylor’s Version) (From the Vault) |
E798592
|
entity |
| Predicate | hasTaylor’sVersion |
P171566
|
FINISHED |
| Object | true |
—
|
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: true | Statement: [Run (Taylor’s Version) (From the Vault), hasTaylor’sVersion, true]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasTaylor’sVersion Context triple: [Run (Taylor’s Version) (From the Vault), hasTaylor’sVersion, true]
-
A.
isTaylor’sVersion
chosen
Indicates that a musical work is the re-recorded “Taylor’s Version” of an original release by Taylor Swift.
-
B.
hasTarn
Indicates that something possesses or contains a tarn, i.e., a small mountain lake or pool.
-
C.
hasVersionIn
Indicates that one entity exists as a specific version or variant within the context, format, or system represented by another entity.
-
D.
Typer
Indicates that one entity serves as the type or classification for another entity.
-
E.
isDubVersionOf
Indicates that one audiovisual work is a dubbed version of another, with its original audio replaced by a different language track while preserving the original content.
- 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_69f224e1932c81908fef14f7b03a10b7 |
completed | April 29, 2026, 3:33 p.m. |
| NER | Named-entity recognition | batch_69f6d16f5cb881908eed141afaaa0b51 |
completed | May 3, 2026, 4:39 a.m. |
| PD | Predicate disambiguation | batch_69f6cfe45554819089cbbd538d992132 |
completed | May 3, 2026, 4:32 a.m. |
Created at: April 29, 2026, 9:15 p.m.