Triple
T22255498
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Dave Gahan |
E550084
|
entity |
| Predicate | collaboratedWith |
P435
|
FINISHED |
| Object | Soulsavers |
—
|
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: Soulsavers | Statement: [Dave Gahan, collaboratedWith, Soulsavers]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Soulsavers Context triple: [Dave Gahan, collaboratedWith, Soulsavers]
-
A.
Soulsavers
chosen
Soulsavers is a British production and remix duo known for their atmospheric blend of electronic, rock, and gospel influences and frequent collaborations with vocalists like Mark Lanegan.
-
B.
Saviours
Saviours is an American heavy metal band known for its blend of stoner, doom, and classic metal influences.
-
C.
Scourged Saviour
Scourged Saviour is a devotional title for Jesus Christ emphasizing his suffering under scourging before the crucifixion.
-
D.
The Suffering
The Suffering is a horror-themed action video game known for its brutal combat, psychological elements, and morally driven narrative set within a haunted prison.
-
E.
Saviour Machine
"Saviour Machine" is a dystopian-themed rock song by David Bowie that critiques authoritarian control and blind faith in technology.
- 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_69e11e42adb8819087714772ea606709 |
completed | April 16, 2026, 5:37 p.m. |
| NER | Named-entity recognition | batch_69f138c1d70881908df47b0f818c0022 |
completed | April 28, 2026, 10:46 p.m. |
Created at: April 16, 2026, 8:39 p.m.