Triple
T14114442
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | On and On |
E339728
|
entity |
| Predicate | hasTitle |
P38
|
FINISHED |
| Object | On and On |
E339728
|
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: On and On | Statement: [On and On, hasTitle, On and On]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: On and On Context triple: [On and On, hasTitle, On and On]
-
A.
On and On
chosen
"On and On" is a song featured on Gemma Hayes' debut album "The 18th Day."
-
B.
On and On
"On and On" is a mellow, acoustic-driven studio album by singer-songwriter Jack Johnson that blends surf-folk melodies with introspective, laid-back lyrics.
-
C.
On and On
"On and On" is a soft rock hit song by singer-songwriter Stephen Bishop, best known for its mellow melody and reflective lyrics that made it a popular track in the late 1970s.
-
D.
On & On
"On & On" is a neo-soul song by Erykah Badu that became her breakout hit and is widely recognized for its distinctive blend of jazz, soul, and hip-hop influences.
-
E.
On and On and On
"On and On and On" is a song by the Swedish pop group ABBA, released in 1980 on their album "Super Trouper."
- 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_69d81c6a95b481909e39111e0c1f31ee |
completed | April 9, 2026, 9:38 p.m. |
| NER | Named-entity recognition | batch_69de600f992c81908133813f2894dcca |
completed | April 14, 2026, 3:41 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69fcd0b881388190a5bcdd87fd10c516 |
completed | May 7, 2026, 5:49 p.m. |
Created at: April 9, 2026, 10:22 p.m.