Triple
T12005681
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Steel Wheels |
E285772
|
entity |
| Predicate | precededBy |
P97
|
FINISHED |
| Object | Dirty Work |
E285771
|
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: Dirty Work | Statement: [Steel Wheels, precededBy, Dirty Work]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Dirty Work Context triple: [Steel Wheels, precededBy, Dirty Work]
-
A.
Dirty Work
chosen
"Dirty Work" is a 1986 studio album by the Rolling Stones, known for its hard rock sound, turbulent recording period, and mixed critical reception.
-
B.
Dirty Work
"Dirty Work" is a soft rock song by Steely Dan, known for its smooth melody, soulful vocals, and themes of infidelity and moral compromise.
-
C.
Slave to the Grind
"Slave to the Grind" is a hard-hitting heavy metal song by American band Skid Row, known for its aggressive sound and socially charged lyrics.
-
D.
Night Job
"Night Job" is a popular hip-hop track by American rapper Bas, featuring J. Cole, known for its dark, introspective lyrics and atmospheric production.
-
E.
Dirty Jobs
Dirty Jobs is a reality television series in which host Mike Rowe explores and participates in some of the dirtiest and most unusual occupations across America.
- 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_69d6ab45a368819084fce08bf0dc3705 |
completed | April 8, 2026, 7:23 p.m. |
| NER | Named-entity recognition | batch_69d903c5cfc08190821e4b2940c51416 |
completed | April 10, 2026, 2:05 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f61e3af3cc8190b2a0e3531713aca5 |
completed | May 2, 2026, 3:54 p.m. |
Created at: April 8, 2026, 9:46 p.m.