Triple
T11597420
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kornél Mundruczó |
E275039
|
entity |
| Predicate | notableWork |
P4
|
FINISHED |
| Object | White God |
E887403
|
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: White God | Statement: [Kornél Mundruczó, notableWork, White God]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: White God Context triple: [Kornél Mundruczó, notableWork, White God]
-
A.
White God
chosen
White God is a 2014 Hungarian drama film directed by Kornél Mundruczó, known for its allegorical story about a girl and her dog amid a violent canine uprising.
-
B.
God Hates Us All
God Hates Us All is a 2001 studio album by American thrash metal band Slayer, known for its aggressive sound and dark, controversial themes.
-
C.
God of Carnage
God of Carnage is a darkly comic stage play by Yasmina Reza that explores the breakdown of civilized behavior when two sets of parents meet to discuss a playground fight between their sons.
-
D.
Mad God
Mad God is a dark, surreal stop-motion animated horror film directed by visual effects legend Phil Tippett, renowned for its nightmarish imagery and decades-long production.
-
E.
Wigger
Wigger is a river in Switzerland that flows through the Aare basin as one of its tributaries.
- 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_69d6aae6b14c81908dc5a74bad7591f9 |
completed | April 8, 2026, 7:22 p.m. |
| NER | Named-entity recognition | batch_69d89549c870819086e16e9110bbad87 |
completed | April 10, 2026, 6:14 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69e8a7cad108819082eebb3ca130f5b8 |
completed | April 22, 2026, 10:49 a.m. |
Created at: April 8, 2026, 9:38 p.m.