Triple
T19534096
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Bent |
E488724
|
entity |
| Predicate | precedesSingle |
P97
|
FINISHED |
| Object | If You’re Gone |
—
|
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: If You’re Gone | Statement: [Bent, precedesSingle, If You’re Gone]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: If You’re Gone Context triple: [Bent, precedesSingle, If You’re Gone]
-
A.
If You're Gone
chosen
"If You're Gone" is a popular rock ballad by American band Matchbox Twenty, known for its emotional lyrics and prominent use of horns.
-
B.
When You’re Gone
"When You’re Gone" is a pop-rock duet by Canadian singer Bryan Adams, best known for its catchy melody and its popular version featuring Melanie C of the Spice Girls.
-
C.
When You’re Gone
"When You’re Gone" is a 2007 pop-rock ballad by Canadian singer Avril Lavigne that reflects on loss and longing in a relationship.
-
D.
So Gone
"So Gone" is an R&B song best known as a 2003 hit single by Monica, produced by Missy Elliott and Kanye West.
-
E.
So Gone
So Gone is a creative work by Jamahl Rye, recognized as one of his notable contributions to his field.
- 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_69d8e8db5b6c8190984b61f91981f575 |
completed | April 10, 2026, 12:11 p.m. |
| NER | Named-entity recognition | batch_69e636417ed88190b4c66a323bca776f |
completed | April 20, 2026, 2:20 p.m. |
Created at: April 10, 2026, 1:41 p.m.