Triple
T5311047
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Walking on Sunshine |
E119026
|
entity |
| Predicate | hasSong |
P20452
|
FINISHED |
| Object | Walking on Sunshine |
E119026
|
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: Walking on Sunshine | Statement: [Walking on Sunshine, hasSong, Walking on Sunshine]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Walking on Sunshine Context triple: [Walking on Sunshine, hasSong, Walking on Sunshine]
-
A.
Walking on Sunshine
chosen
"Walking on Sunshine" is a 2014 British jukebox musical romantic comedy film set in Italy, featuring popular 1980s songs and an ensemble cast including Greg Wise.
-
B.
Wake Me Up Before You Go-Go
"Wake Me Up Before You Go-Go" is a 1984 upbeat pop song by Wham! that became one of the duo’s signature hits and a defining anthem of 1980s dance-pop.
-
C.
Don’t Stop
"Don’t Stop" is a track by Snoop Dogg featured on his 2006 studio album *Tha Blue Carpet Treatment*.
-
D.
Joy (Takes Over Me)
"Joy (Takes Over Me)" is a song featured on the album *Signed, Sealed & Delivered*.
-
E.
Shine On
"Shine On" is a song featured on James Blunt's 2007 studio album "All the Lost Souls."
- 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_69bd446b57bc8190a513d2e6c40314f3 |
completed | March 20, 2026, 12:58 p.m. |
| NER | Named-entity recognition | batch_69bd85343ae08190bd9801ea4eac7003 |
completed | March 20, 2026, 5:34 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69bf11033c448190ab64600913ee8a9c |
completed | March 21, 2026, 9:43 p.m. |
Created at: March 20, 2026, 1:53 p.m.