Triple
T22299719
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Undertow |
E551222
|
entity |
| Predicate | notableSingle |
P3283
|
FINISHED |
| Object | Sober |
—
|
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: Sober | Statement: [Undertow, notableSingle, Sober]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Sober Context triple: [Undertow, notableSingle, Sober]
-
A.
Sober
chosen
"Sober" is a deeply personal pop ballad by Demi Lovato in which she candidly addresses a relapse in her sobriety and struggles with addiction.
-
B.
Sober
"Sober" is a pop song by American singer Jennifer Paige, best known as the follow-up single to her hit "Crush."
-
C.
Sober
"Sober" is a soulful, genre-blending R&B/hip-hop track by Childish Gambino known for its smooth vocals, emotional lyrics, and inventive production.
-
D.
Soberish
Soberish is a 2021 studio album by American singer-songwriter Liz Phair that marks her return to indie rock after a long hiatus.
-
E.
Clean and Sober
Clean and Sober is a 1988 drama film in which Michael Keaton plays a real-estate agent struggling with cocaine addiction and entering rehab, marking one of his first major serious, non-comedic roles.
- 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_69e11e46c0188190800181a4233f28fe |
completed | April 16, 2026, 5:37 p.m. |
| NER | Named-entity recognition | batch_69f15722c3348190b63eb49764ef132d |
completed | April 29, 2026, 12:56 a.m. |
Created at: April 16, 2026, 8:41 p.m.