Triple
T32148328
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Peter Egermann |
E821083
|
entity |
| Predicate | relatedWorkCharacterOf |
—
|
GENERATED |
| Object | Scenes from a Marriage |
—
|
UNRECOGNIZED GENERATED |
How this triple was built (1 step)
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.
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: relatedWorkCharacterOf Context triple: [Peter Egermann, relatedWorkCharacterOf, Scenes from a Marriage]
-
A.
relatedWorkOfPerson
Indicates that a work (such as a publication, project, or creation) is associated with or produced by a particular person.
-
B.
relatedCharacter
Indicates that one character has a specified relationship or association with another character.
-
C.
workCharacter
chosen
Indicates that a person is a fictional or narrative character appearing in a particular creative work.
-
D.
relatedCharacterContext
Indicates a contextual relationship between characters, such as roles, interactions, or situational connections that link them within a specific narrative or setting.
-
E.
relatedWorkForm
Indicates a relationship in which one work is connected to another through a different form or version (e.g., adaptation, translation, or other format variation).
- F. None of above.
Provenance (1 batch)
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_69f3490520d081909b2f1271dab75faa |
completed | April 30, 2026, 12:20 p.m. |
Created at: May 1, 2026, 12:31 a.m.