Triple
T15949320
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | DJ Frank E |
E386771
|
entity |
| Predicate | workedOn |
P3
|
FINISHED |
| Object | “Sober” by P!nk |
E583171
|
NE FINISHED |
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” by P!nk | Statement: [DJ Frank E, workedOn, “Sober” by P!nk]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: “Sober” by P!nk Context triple: [DJ Frank E, workedOn, “Sober” by P!nk]
-
A.
Sober (Pink song)
chosen
"Sober" is a pop-rock song by American singer Pink, known for its introspective lyrics about temptation, addiction, and self-control.
-
B.
single "Sober"
"Sober" is a pop single by American singer Jennifer Paige, best known for her late-1990s hit "Crush."
-
C.
Mother I Sober
"Mother I Sober" is a deeply introspective and emotionally raw song by Kendrick Lamar that confronts generational trauma, abuse, and the struggle for healing and forgiveness.
-
D.
Hate Bein' Sober
"Hate Bein' Sober" is a popular hip-hop track by Chief Keef featuring 50 Cent and Wiz Khalifa, known for its hard-hitting production and party-centric, rebellious lyrics.
-
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 (3 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_69d86da882448190a82ea962fe343b79 |
completed | April 10, 2026, 3:25 a.m. |
| NER | Named-entity recognition | batch_69e156d3cc04819097367369a78d6ef2 |
completed | April 16, 2026, 9:38 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ffbe76df6481909f8246099faa377a |
completed | May 9, 2026, 11:08 p.m. |
Created at: April 10, 2026, 4:53 a.m.