Triple
T20408133
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Under My Skin |
E500522
|
entity |
| Predicate | hasPart |
P35
|
FINISHED |
| Object | Take Me Away |
—
|
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: Take Me Away | Statement: [Under My Skin, hasPart, Take Me Away]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Take Me Away Context triple: [Under My Skin, hasPart, Take Me Away]
-
A.
Take Me Away
chosen
"Take Me Away" is a song featured on the album "Evolver."
-
B.
Take You Away
"Take You Away" is a song featured on Michael Bublé’s studio album "Nobody but Me."
-
C.
Move Away
"Move Away" is a 1986 pop single by British band Culture Club, known for its catchy melody and polished production during the later phase of their career.
-
D.
Take It Away
"Take It Away" is a song by Paul McCartney, released in 1982 and known for its melodic pop-rock style and appearance on his album "Tug of War."
-
E.
Take Me
"Take Me" is a 2017 dark comedy film about a struggling entrepreneur who runs a simulated kidnapping service that spirals out of control when he takes on an unusually mysterious client.
- 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_69e67a3d03ac81908f37b907ccbb5088 |
completed | April 20, 2026, 7:10 p.m. |
Created at: April 16, 2026, 11:29 a.m.