Triple
T9678103
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | The World Tonight |
E234210
|
entity |
| Predicate | hasBside |
P15273
|
FINISHED |
| Object | Used to Be Bad |
E234216
|
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: Used to Be Bad | Statement: [The World Tonight, hasBside, Used to Be Bad]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Used to Be Bad Context triple: [The World Tonight, hasBside, Used to Be Bad]
-
A.
Used to Be Bad
chosen
"Used to Be Bad" is a blues-influenced rock song by Paul McCartney and Steve Miller, featured on McCartney's 1997 album "Flaming Pie."
-
B.
Let’s Be Bad
"Let’s Be Bad" is a high-energy musical number from the TV series Smash, performed within the fictional Marilyn Monroe musical Bombshell.
-
C.
Good to Be Bad
Good to Be Bad is a 2008 hard rock studio album by British band Whitesnake, marking their return with new material after a long hiatus.
-
D.
Born to Be Bad
Born to Be Bad is a 1950 film noir–style drama starring Joan Fontaine as a manipulative social climber entangled in romance and deceit.
-
E.
So Bad
"So Bad" is a melodic pop ballad by Paul McCartney, released in the early 1980s and noted for its smooth vocals and sentimental lyrics.
- 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_69ca84c99e34819092e5563a7106cfca |
completed | March 30, 2026, 2:12 p.m. |
| NER | Named-entity recognition | batch_69cd9c9b01708190aaf51cf4d36015a0 |
completed | April 1, 2026, 10:30 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d18a34adec8190a4a260d029e408aa |
completed | April 4, 2026, 10:01 p.m. |
Created at: March 30, 2026, 8:16 p.m.