Triple
T11528076
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Knecht Ruprecht |
E273349
|
entity |
| Predicate | relatedConcept |
P37
|
FINISHED |
| Object | Krampus |
E273350
|
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: Krampus | Statement: [Knecht Ruprecht, relatedConcept, Krampus]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Krampus Context triple: [Knecht Ruprecht, relatedConcept, Krampus]
-
A.
Krampus
chosen
Krampus is a horned, demonic figure from Central European folklore who punishes misbehaving children during the Christmas season, often appearing alongside Saint Nicholas.
-
B.
Krampus (2015 film)
Krampus (2015 film) is a 2015 horror-comedy movie that blends dark folklore and holiday themes, following a dysfunctional family terrorized by the demonic Christmas figure Krampus.
-
C.
Krampus: Shadow of Saint Nicholas
Krampus: Shadow of Saint Nicholas is a horror-comedy graphic novel that expands on the dark folklore of Krampus through interconnected holiday-themed tales.
-
D.
Klaus
Klaus is a masculine given name of German origin commonly used in German-speaking countries.
-
E.
Trick 'r Treat
Trick 'r Treat is a 2007 anthology horror film that interweaves multiple Halloween-themed stories and has become a cult favorite for its darkly comedic tone and inventive storytelling.
- 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_69d6aae3fbec8190a14632a5df2538b6 |
completed | April 8, 2026, 7:22 p.m. |
| NER | Named-entity recognition | batch_69d883972b10819093bd09cf8406671c |
completed | April 10, 2026, 4:59 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69e6256e3130819095a93c8d1891b078 |
completed | April 20, 2026, 1:09 p.m. |
Created at: April 8, 2026, 9:37 p.m.