Triple
T6678492
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Lucy Pearl |
E151916
|
entity |
| Predicate | hasSingle |
P3282
|
FINISHED |
| Object | Dance Tonight |
E611529
|
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: Dance Tonight | Statement: [Lucy Pearl, hasSingle, Dance Tonight]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Dance Tonight Context triple: [Lucy Pearl, hasSingle, Dance Tonight]
-
A.
Dance Tonight
chosen
"Dance Tonight" is a hit R&B single by the supergroup Lucy Pearl, known for its smooth groove and blend of soul, hip-hop, and funk influences.
-
B.
Dance the Night
"Dance the Night" is a disco-pop song by Dua Lipa, best known for its inclusion on the soundtrack of the 2023 film *Barbie*.
-
C.
Dance with Me Tonight
"Dance with Me Tonight" is a retro-inspired pop song by English singer Olly Murs, known for its upbeat, soulful style and catchy, sing-along chorus.
-
D.
Tonight, Tonight
"Tonight, Tonight" is a 1996 orchestral alternative rock song by The Smashing Pumpkins, known for its lush string arrangement and iconic, Méliès-inspired music video.
-
E.
Dance for You
"Dance for You" is an R&B song by The-Dream, known for its sensual slow-jam style and smooth, intimate production.
- 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_69c687f830bc81909eb8b04dbb8450b1 |
completed | March 27, 2026, 1:36 p.m. |
| NER | Named-entity recognition | batch_69c6b0f6813c8190906f619b4276a232 |
completed | March 27, 2026, 4:31 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c700790c388190bba9f0440470ebf5 |
completed | March 27, 2026, 10:11 p.m. |
Created at: March 27, 2026, 2:03 p.m.