Triple
T21463337
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ken Russell |
E529528
|
entity |
| Predicate | directed |
P7373
|
FINISHED |
| Object | Savage Messiah |
—
|
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: Savage Messiah | Statement: [Ken Russell, directed, Savage Messiah]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Savage Messiah Context triple: [Ken Russell, directed, Savage Messiah]
-
A.
Savage Messiah
chosen
Savage Messiah is a 1972 British biographical drama film about the life of French sculptor Henri Gaudier-Brzeska, directed by Ken Russell.
-
B.
Wall of Voodoo
Wall of Voodoo was an American new wave band best known for their 1982 hit single "Mexican Radio," which blended post-punk, electronic, and spaghetti western influences.
-
C.
Burnin’ Alive
"Burnin’ Alive" is a hard rock song by Australian band AC/DC from their 1995 album *Ballbreaker*.
-
D.
Damned
Damned is a darkly comic horror novel by Chuck Palahniuk that follows a dead teenage girl navigating a satirical version of Hell.
-
E.
Kill Us All
"Kill Us All" is a track by the American rapper Kamikaze, known for its aggressive style and intense lyrical delivery.
- 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_69e0c458133481908ae8b41a12c4edec |
completed | April 16, 2026, 11:13 a.m. |
| NER | Named-entity recognition | batch_69e9e9efdb188190be79b72e1bd18860 |
completed | April 23, 2026, 9:44 a.m. |
Created at: April 16, 2026, 6:09 p.m.