Triple
T28998886
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Dusty Trails (Demo) |
E736243
|
entity |
| Predicate | demoVersionOf |
P31922
|
FINISHED |
| Object | Dusty Trails |
—
|
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: Dusty Trails | Statement: [Dusty Trails (Demo), demoVersionOf, Dusty Trails]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: demoVersionOf Context triple: [Dusty Trails (Demo), demoVersionOf, Dusty Trails]
-
A.
versionOf
chosen
Indicates that one entity is a specific form, edition, or variant derived from or corresponding to another entity.
-
B.
versionExample
Indicates that one entity serves as an example or illustrative instance of a particular version of another entity.
-
C.
hasAcousticDemoVersion
Indicates that an entity has a version or recording presented in an acoustic demo form.
-
D.
developerPreviewFor
Indicates a relationship where one entity serves as a developer-focused preview or early-access version of another entity.
-
E.
exportVersionOf
Indicates that one entity is a version of another specifically created or designated for export (e.g., for external distribution or use).
- 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_69f077eacd0481908ef0bafd74491cd0 |
completed | April 28, 2026, 9:03 a.m. |
| NER | Named-entity recognition | batch_69f65fb930408190a871ef5be8ca99cf |
completed | May 2, 2026, 8:34 p.m. |
| PD | Predicate disambiguation | batch_69f659d297cc8190b2b962ba30a1edb3 |
completed | May 2, 2026, 8:08 p.m. |
Created at: April 28, 2026, 9:33 a.m.