Triple
T27690617
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Feels Like We Only Go Backwards |
E698144
|
entity |
| Predicate | originAlbumArtistNationality |
P196171
|
FINISHED |
| Object | Australian |
—
|
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: Australian | Statement: [Feels Like We Only Go Backwards, originAlbumArtistNationality, Australian]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: originAlbumArtistNationality Context triple: [Feels Like We Only Go Backwards, originAlbumArtistNationality, Australian]
-
A.
primaryArtistNationality
Indicates the nationality associated with the main or primary artist involved in a work or context.
-
B.
associated artist nationality
Indicates the country or nationality with which an artist connected to the subject is identified.
-
C.
coArtistNationality
Indicates that two artists who have collaborated share the same nationality.
-
D.
featuredArtistNationality
Indicates the nationality associated with an artist who is prominently featured in a work or event.
-
E.
coverArtistNationality
Indicates the nationality of the artist who created the cover for a work.
- F. None of above. chosen
Provenance (4 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_69ef590df8708190af5488f0638e790c |
completed | April 27, 2026, 12:39 p.m. |
| NER | Named-entity recognition | batch_69fe12a899d4819080d48423f32eace9 |
completed | May 8, 2026, 4:43 p.m. |
| PD | Predicate disambiguation | batch_69fe0d7f6aa08190a1d2dfc025d4e0dc |
completed | May 8, 2026, 4:21 p.m. |
| PDg | Predicate description generation | batch_69fe12a769c08190bc445d302d2e8f98 |
completed | May 8, 2026, 4:43 p.m. |
Created at: April 27, 2026, 2:51 p.m.