Triple
T22071167
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Cotton Candy |
E545408
|
entity |
| Predicate | follows |
P134
|
FINISHED |
| Object | Sugar Lips |
—
|
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: Sugar Lips | Statement: [Cotton Candy, follows, Sugar Lips]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Sugar Lips Context triple: [Cotton Candy, follows, Sugar Lips]
-
A.
Sugar Lips
chosen
"Sugar Lips" is a popular jazz trumpet tune by Al Hirt that became one of his signature hits in the 1960s.
-
B.
Red Lips
"Red Lips" is a 2012 electropop/grunge-influenced single by American singer Sky Ferreira, known for its abrasive sound and collaboration with producer Greg Kurstin.
-
C.
Hot Lips
Hot Lips is the nickname of Major Margaret Houlihan, the strict yet evolving head nurse character from the M*A*S*H franchise.
-
D.
Hot Lips
Hot Lips is the nickname of Oran "Hot Lips" Page, an influential American jazz trumpeter and vocalist known for his powerful playing and contributions to the swing era.
-
E.
Lips Like Sugar
"Lips Like Sugar" is a 1987 alternative rock song by Echo & the Bunnymen, known for its atmospheric sound and enduring popularity as one of the band's signature tracks.
- 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_69e11e344dfc81909b1d88a7221329c7 |
completed | April 16, 2026, 5:36 p.m. |
| NER | Named-entity recognition | batch_69f128881af481909b28cda2d343f4e3 |
completed | April 28, 2026, 9:37 p.m. |
Created at: April 16, 2026, 8:28 p.m.