Triple
T34161313
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Wütende Heer |
E876283
|
entity |
| Predicate | hasMotifElement |
P182389
|
FINISHED |
| Object | wild hunt |
—
|
LITERAL 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: wild hunt | Statement: [Wütende Heer, hasMotifElement, wild hunt]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasMotifElement Context triple: [Wütende Heer, hasMotifElement, wild hunt]
-
A.
hasTypeOfMotif
chosen
Indicates that one entity features or is characterized by a specific kind or category of motif.
-
B.
hasMotiveElement
Indicates that one entity includes, specifies, or is characterized by a particular motive-related component or factor in a broader relationship or action.
-
C.
hasMottoElement
Indicates that something includes a specific phrase or component as part of its motto.
-
D.
hasMirrorMotif
Indicates that one entity features a mirror-related motif or pattern in relation to another entity or context.
-
E.
hasTitleMotif
Indicates that a work’s title prominently features or reflects a recurring motif or central thematic element within the work.
- F. None of above.
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_69f349ac987481908a8e6053f665bc8b |
completed | April 30, 2026, 12:23 p.m. |
| NER | Named-entity recognition | batch_69feba0f09508190b3e871c62b19ec7f |
completed | May 9, 2026, 4:37 a.m. |
| PD | Predicate disambiguation | batch_69feb957fe7c8190969fb31a6d1a59c8 |
completed | May 9, 2026, 4:34 a.m. |
Created at: May 1, 2026, 1:54 a.m.