Triple
T20410312
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | We Sing. We Dance. We Steal Things. |
E500570
|
entity |
| Predicate | hasPart |
P35
|
FINISHED |
| Object | Only Human |
—
|
NE NERFINISHED |
How this triple was built (3 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: Only Human | Statement: [We Sing. We Dance. We Steal Things., hasPart, Only Human]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Only Human Context triple: [We Sing. We Dance. We Steal Things., hasPart, Only Human]
-
A.
Only Human
"Only Human" is a catchy, reggae-influenced pop song by the Jonas Brothers from their 2019 comeback album "Happiness Begins."
-
B.
Only Human
Only Human is a Doctor Who tie-in novel by Gareth Roberts that features the Ninth Doctor, Rose Tyler, and Captain Jack Harkness in a time-travel adventure involving Neanderthals and modern-day London.
-
C.
Just Like Heaven
Just Like Heaven is a 2005 romantic comedy-fantasy film starring Reese Witherspoon and Mark Ruffalo, centered on a man who falls in love with the spirit of a woman haunting his apartment.
-
D.
Just Like Heaven
"Just Like Heaven" is a 1987 dream-pop love song by English rock band The Cure, widely regarded as one of their signature and most influential tracks.
-
E.
Everybody Wants to Rule the World
"Everybody Wants to Rule the World" is a 1985 synth-pop/new wave song by Tears for Fears, widely regarded as one of the band's signature hits and an iconic track of the 1980s.
- F. None of above. chosen
- G. Unsure - the case is ambiguous/there is not enough information to decide.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Only Human Target entity description: "Only Human" is a song by American singer-songwriter Jason Mraz from his album *We Sing. We Dance. We Steal Things.*
-
A.
Only Human
"Only Human" is a catchy, reggae-influenced pop song by the Jonas Brothers from their 2019 comeback album "Happiness Begins."
-
B.
Only Human
Only Human is a Doctor Who tie-in novel by Gareth Roberts that features the Ninth Doctor, Rose Tyler, and Captain Jack Harkness in a time-travel adventure involving Neanderthals and modern-day London.
-
C.
Just Like Heaven
"Just Like Heaven" is a 1987 dream-pop love song by English rock band The Cure, widely regarded as one of their signature and most influential tracks.
-
D.
Just Like Heaven
Just Like Heaven is a 2005 romantic comedy-fantasy film starring Reese Witherspoon and Mark Ruffalo, centered on a man who falls in love with the spirit of a woman haunting his apartment.
-
E.
Everybody Wants to Rule the World
"Everybody Wants to Rule the World" is a 1985 synth-pop/new wave song by Tears for Fears, widely regarded as one of the band's signature hits and an iconic track of the 1980s.
- F. None of above. chosen
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.