Triple
T10007682
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | What's Inside: Songs from Waitress |
E198292
|
entity |
| Predicate | notableTrack |
P8087
|
FINISHED |
| Object | She Used to Be Mine |
E198296
|
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: She Used to Be Mine | Statement: [What's Inside: Songs from Waitress, notableTrack, She Used to Be Mine]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: She Used to Be Mine Context triple: [What's Inside: Songs from Waitress, notableTrack, She Used to Be Mine]
-
A.
She Used to Be Mine
chosen
"She Used to Be Mine" is an emotional ballad by Sara Bareilles, best known as the signature song from the Broadway musical *Waitress*, reflecting themes of regret, self-reflection, and resilience.
-
B.
When You Were Mine
"When You Were Mine" is a synth-pop song by Prince, known for its bittersweet lyrics about unrequited love and later popularized further by Cyndi Lauper’s cover version.
-
C.
Be Mine
"Be Mine" is a track featured on the album "Boys & Girls."
-
D.
Be Mine
"Be Mine" is a song featured on the album "What Comes Naturally."
-
E.
Are You Really Mine
"Are You Really Mine" is a country music song recorded by American singer Jimmie Rodgers that became one of his notable hits.
- 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_69ca830fcca48190bbbd9b20c233835f |
completed | March 30, 2026, 2:05 p.m. |
| NER | Named-entity recognition | batch_69cdcd187fe481908556ea896c528ea4 |
completed | April 2, 2026, 1:57 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d2b5f15c6c8190b52924d6f86d63e0 |
completed | April 5, 2026, 7:20 p.m. |
Created at: March 30, 2026, 8:52 p.m.