Triple
T35265618
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Come Thru |
E1018503
|
entity |
| Predicate | isBonusTrackOnEdition |
P85255
|
FINISHED |
| Object | deluxe edition of Nothing Was the Same |
—
|
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: deluxe edition of Nothing Was the Same | Statement: [Come Thru, isBonusTrackOnEdition, deluxe edition of Nothing Was the Same]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: isBonusTrackOnEdition Context triple: [Come Thru, isBonusTrackOnEdition, deluxe edition of Nothing Was the Same]
-
A.
isBonusEditionOf
Indicates that one item is a special bonus version or supplementary edition of another primary item.
-
B.
hasBonusTrackStatus
chosen
Indicates whether an item (such as a track or release) is designated as a bonus track in relation to a primary work or edition.
-
C.
containsAdditionalTracksBeyond
Indicates that one entity includes more tracks or items than are present in another referenced set or version.
-
D.
hasDeluxeEditionTrackCount
Indicates the number of tracks included in the deluxe edition of a given release or work.
-
E.
isBsideTrack
Indicates that one track is the B-side counterpart associated with another primary (A-side) track, typically on a single release.
- 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_69f76de4be5c8190a51705c07612cac8 |
completed | May 3, 2026, 3:46 p.m. |
| NER | Named-entity recognition | batch_69f78f9a095881908d7d5d1914afae77 |
completed | May 3, 2026, 6:10 p.m. |
| PD | Predicate disambiguation | batch_69f78e2f52e08190a77661223a96c601 |
completed | May 3, 2026, 6:04 p.m. |
Created at: May 3, 2026, 4:02 p.m.