Triple
T17511483
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | The Paramour Sessions |
E426460
|
entity |
| Predicate | hasPart |
P35
|
FINISHED |
| Object | What Do You Do? |
—
|
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: What Do You Do? | Statement: [The Paramour Sessions, hasPart, What Do You Do?]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: What Do You Do? Context triple: [The Paramour Sessions, hasPart, What Do You Do?]
-
A.
What Do You Do?
"What Do You Do?" is a pop song by British singer Jess Glynne, showcasing her soulful vocals and emotive, introspective lyricism.
-
B.
What Do You Do
chosen
"What Do You Do" is a song by Scottish band The Proclaimers, featured on their 1988 album *Sunshine on Leith*.
-
C.
How Do You Do It?
"How Do You Do It?" is a 1963 pop song that became a major hit single for the British Merseybeat band Gerry and the Pacemakers.
-
D.
What's That You're Doing?
"What's That You're Doing?" is a song by Paul McCartney and Stevie Wonder, featured on McCartney's 1982 album "Tug of War."
-
E.
What Can I Do for You?
"What Can I Do for You?" is a 1974 funk-infused soul track by the American vocal group Labelle, showcasing their powerful harmonies and socially conscious style.
- 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_69d889dd9164819087b1dc3c9240c870 |
completed | April 10, 2026, 5:25 a.m. |
| NER | Named-entity recognition | batch_69e4525c21c88190a9394c4bce006a38 |
completed | April 19, 2026, 3:56 a.m. |
Created at: April 10, 2026, 5:48 a.m.