Triple
T20852586
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mardi Gras |
E513399
|
entity |
| Predicate | hasSingle |
P3282
|
FINISHED |
| Object | Someday Never Comes |
—
|
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: Someday Never Comes | Statement: [Mardi Gras, hasSingle, Someday Never Comes]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Someday Never Comes Context triple: [Mardi Gras, hasSingle, Someday Never Comes]
-
A.
Someday Never Comes
chosen
"Someday Never Comes" is a reflective rock song by Creedence Clearwater Revival, known as one of the band’s final and most poignant singles.
-
B.
Nobody Someday
"Nobody Someday" is a song best known as the B-side to Robbie Williams' 2001 single "Eternity/The Road to Mandalay."
-
C.
Someday Soon
"Someday Soon" is a song featured on the album "Looking Forward" by Crosby, Stills, Nash & Young.
-
D.
Someday Soon
"Someday Soon" is a song featured on the album "Departure" by the South Korean boy band TVXQ.
-
E.
Someday Soon
Someday Soon is a popular folk-country song written by Canadian singer-songwriter Ian Tyson, widely known through recordings by artists such as Judy Collins.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69e0b4f4898081908209e58edb8f9c45 |
completed | April 16, 2026, 10:07 a.m. |
| NER | Named-entity recognition | batch_69e6c3a4df5c8190aa0e7684ad6fc9f2 |
completed | April 21, 2026, 12:24 a.m. |
Created at: April 16, 2026, 12:44 p.m.