Triple
T20410441
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Save Me, San Francisco |
E500573
|
entity |
| Predicate | containsSong |
P20452
|
FINISHED |
| Object | Marry Me |
—
|
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: Marry Me | Statement: [Save Me, San Francisco, containsSong, Marry Me]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Marry Me Context triple: [Save Me, San Francisco, containsSong, Marry Me]
-
A.
Marry Me
"Marry Me" is a 2022 romantic comedy film starring Jennifer Lopez and Owen Wilson, centered on a pop star who impulsively marries a stranger from the crowd during a live concert.
-
B.
Marry Me
Marry Me is the 2007 debut studio album by American musician St. Vincent, showcasing her eclectic art rock and baroque pop style.
-
C.
Marry Me
"Marry Me" is a song featured on Yemi Alade’s album *Mama Africa*, showcasing her Afro-pop style and vibrant vocal performance.
-
D.
Marry Me
chosen
"Marry Me" is a pop-rock song by the American band Train, best known as a romantic ballad that became popular at weddings and on adult contemporary radio.
-
E.
Marry Me (album)
"Marry Me" is a pop album by English singer-songwriter Olly Murs, showcasing his upbeat, radio-friendly style and catchy, contemporary 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_69e0b4a935588190b9446a99b37ced44 |
completed | April 16, 2026, 10:06 a.m. |
| NER | Named-entity recognition | batch_69e67a3ecb348190ae777f6276037828 |
completed | April 20, 2026, 7:10 p.m. |
Created at: April 16, 2026, 11:29 a.m.