Triple
T21327786
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Herman Cohen |
E525806
|
entity |
| Predicate | workedOn |
P3
|
FINISHED |
| Object | Berserk! |
—
|
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: Berserk! | Statement: [Herman Cohen, workedOn, Berserk!]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Berserk! Context triple: [Herman Cohen, workedOn, Berserk!]
-
A.
Berserk!
chosen
Berserk! is a 1967 British horror–thriller film starring Joan Crawford as a ruthless circus owner entangled in a series of gruesome murders under the big top.
-
B.
Berserk
Berserk is a dark fantasy manga series by Kentaro Miura, renowned for its brutal medieval setting, complex characters, and intricate artwork.
-
C.
Berserker Man
Berserker Man is a science fiction novel by Fred Saberhagen set in his Berserker universe, exploring humanity’s struggle against intelligent, planet-destroying machines.
-
D.
Going Berserk
Going Berserk is a 1983 slapstick comedy film starring John Candy as a hapless chauffeur entangled in a chaotic web of crime, cults, and political assassination plots.
-
E.
The Berzerker
The Berzerker is an Australian extreme metal band known for its ultra-fast, industrial-influenced death/grind sound and use of distorted, noise-laden production.
- 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_69e0b51b90788190a4dd823d962626da |
completed | April 16, 2026, 10:08 a.m. |
| NER | Named-entity recognition | batch_69e7ab4d69b4819088649e34213d0b67 |
completed | April 21, 2026, 4:52 p.m. |
Created at: April 16, 2026, 4:41 p.m.