Triple
T1256711
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Erykah Badu |
E12409
|
entity |
| Predicate | notableSong |
P4
|
FINISHED |
| Object | On & On |
E144144
|
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 & On | Statement: [Erykah Badu, notableSong, On & On]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: On & On Context triple: [Erykah Badu, notableSong, On & On]
-
A.
On & On
chosen
"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.
-
B.
On Our Own
On Our Own is a 1989 R&B/new jack swing single by Bobby Brown, best known as the theme song for the film "Ghostbusters II."
-
C.
The Come On
"The Come On" is a 1956 film noir crime drama starring Sterling Hayden, known for its tale of deception, murder, and double-crosses.
-
D.
On to the Next One
"On to the Next One" is a high-energy hip hop track by Jay-Z featuring production and vocals from Swizz Beatz, known for its minimalist beat and visually striking black-and-white music video.
-
E.
Over and Over
"Over and Over" is a 2004 country-rap crossover single by American rapper Nelly featuring Tim McGraw that became a major international hit.
- 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_69a4933352e08190ac617291985e76c0 |
completed | March 1, 2026, 7:27 p.m. |
| NER | Named-entity recognition | batch_69a4bfa8cfa08190ac49c437a94a843c |
completed | March 1, 2026, 10:37 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ac9980a2a4819094ab26ac390476be |
completed | March 7, 2026, 9:32 p.m. |
Created at: March 1, 2026, 7:50 p.m.