Triple
T17456304
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Bittersweet World |
E425035
|
entity |
| Predicate | hasTrack |
P3284
|
FINISHED |
| Object | Hot Stuff |
—
|
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: Hot Stuff | Statement: [Bittersweet World, hasTrack, Hot Stuff]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Hot Stuff Context triple: [Bittersweet World, hasTrack, Hot Stuff]
-
A.
Hot Stuff
"Hot Stuff" is a 1979 disco hit by Donna Summer that blends dance rhythms with rock influences and became one of her signature songs.
-
B.
Hot Stuff
chosen
"Hot Stuff" is a song featured on the album "Come an’ Get It," likely a rock or pop track known for its energetic, catchy style.
-
C.
Hot Thing
"Hot Thing" is a funk-infused track by Prince from his acclaimed 1987 double album *Sign o’ the Times*, noted for its sensual lyrics and dance-driven groove.
-
D.
Hot Hot Hot
"Hot Hot Hot" is a song best known as the B-side to the English post-punk band The Cure’s single "The Walk."
-
E.
Hot Shot
"Hot Shot" is a 2000 reggae fusion studio album by Jamaican artist Shaggy that achieved global success with hits like "It Wasn't Me" and "Angel."
- 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_69d889db0ba481908402409af3b37917 |
completed | April 10, 2026, 5:25 a.m. |
| NER | Named-entity recognition | batch_69e45141e1d48190b7de9159f1fd71fa |
completed | April 19, 2026, 3:51 a.m. |
Created at: April 10, 2026, 5:47 a.m.