Triple
T22768486
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Overlord |
E563189
|
entity |
| Predicate | composer |
P1361
|
FINISHED |
| Object | Jed Kurzel |
—
|
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: Jed Kurzel | Statement: [Overlord, composer, Jed Kurzel]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Jed Kurzel Context triple: [Overlord, composer, Jed Kurzel]
-
A.
Jed Kurzel
chosen
Jed Kurzel is an Australian film composer and musician known for his atmospheric scores for films such as "Slow West," "Snowtown," and "Macbeth."
-
B.
Justin Kurzel
Justin Kurzel is an Australian film director known for his visually striking and often dark adaptations, including the 2015 film "Macbeth" and the true-crime drama "Snowtown."
-
C.
David Michôd
David Michôd is an Australian film director and screenwriter best known for his crime drama "Animal Kingdom" and dystopian thriller "The Rover."
-
D.
Martin Arjovsky
Martin Arjovsky is a machine learning researcher best known for introducing the Wasserstein GAN, a generative adversarial network variant that improves training stability and sample quality.
-
E.
Peter Strickland
Peter Strickland is a British filmmaker known for his atmospheric, genre-bending films that blend psychological horror, dark humor, and meticulous sound design.
- 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_69e24552e11c81909c2d61578a558bd7 |
completed | April 17, 2026, 2:36 p.m. |
| NER | Named-entity recognition | batch_69f17b59c9cc8190a6edd68f3209a672 |
completed | April 29, 2026, 3:30 a.m. |
Created at: April 17, 2026, 3:27 p.m.