Triple
T32490610
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | In Visible Silence |
E830372
|
entity |
| Predicate | featureOnTrack |
P162260
|
FINISHED |
| Object | Duane Eddy – "Peter Gunn" |
—
|
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: Duane Eddy – "Peter Gunn" | Statement: [In Visible Silence, featureOnTrack, Duane Eddy – "Peter Gunn"]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: featureOnTrack Context triple: [In Visible Silence, featureOnTrack, Duane Eddy – "Peter Gunn"]
-
A.
trackFeature
Indicates that one entity monitors, records, or follows the behavior, state, or evolution of a particular feature associated with another entity.
-
B.
hasTrackFeatures
Indicates that something possesses or is associated with specific track-related characteristics or attributes.
-
C.
feat
chosen
Indicates that an entity features, includes, or prominently presents another entity as part of its content or composition.
-
D.
trackOn
Indicates that one entity is physically positioned or moving along the surface or path of another, like a vehicle on a track or rails.
-
E.
featuredOnSong
Indicates that an entity (such as an artist) appears as a guest or secondary contributor on a particular song.
- 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_69f34920aa4081908d8fb0277414b911 |
completed | April 30, 2026, 12:20 p.m. |
| NER | Named-entity recognition | batch_6a01185c46f0819089b4a2ad3c3e2f33 |
completed | May 10, 2026, 11:44 p.m. |
| PD | Predicate disambiguation | batch_6a0117e19e008190870663dd45084416 |
completed | May 10, 2026, 11:42 p.m. |
Created at: May 1, 2026, 12:59 a.m.