Triple
T15950855
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | The Revival |
E386813
|
entity |
| Predicate | hasPart |
P35
|
FINISHED |
| Object | Feels Good |
E386801
|
NE 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: Feels Good | Statement: [The Revival, hasPart, Feels Good]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Feels Good Context triple: [The Revival, hasPart, Feels Good]
-
A.
Feels Good
chosen
"Feels Good" is a 1990 new jack swing and R&B hit single by Tony! Toni! Toné! that became one of the group's signature songs.
-
B.
Feels Good
"Feels Good" is a popular jazz composition closely associated with the German a cappella group Take 6, showcasing their intricate harmonies and innovative vocal arrangements.
-
C.
Good Feeling
"Good Feeling" is the debut studio album by Scottish rock band Travis, showcasing their early Britpop-influenced sound.
-
D.
Feel Good
"Feel Good" is a popular song by the American funk band The Internet, known for its smooth neo-soul sound and laid-back groove.
-
E.
Feel Good
"Feel Good" is a song by American singer, songwriter, and producer Syd (Sydney Loren Bennett), showcasing her smooth, minimalist R&B style.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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_69d86da882448190a82ea962fe343b79 |
completed | April 10, 2026, 3:25 a.m. |
| NER | Named-entity recognition | batch_69e156d59f5081909f6a81d578c4e2e8 |
completed | April 16, 2026, 9:38 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ffbe78a76481909622d7a2443cba4d |
completed | May 9, 2026, 11:08 p.m. |
Created at: April 10, 2026, 4:53 a.m.