Triple
T32148328
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Peter Egermann |
E821083
|
entity |
| Predicate | relatedWorkCharacterOf |
P72625
|
FINISHED |
| Object | Scenes from a Marriage |
E1916108
|
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: Scenes from a Marriage | Statement: [Peter Egermann, relatedWorkCharacterOf, Scenes from a Marriage]
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 (4 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_69f3490520d081909b2f1271dab75faa |
completed | April 30, 2026, 12:20 p.m. |
| NER | Named-entity recognition | batch_6a037c894b488190bcbec2eccaff4a01 |
completed | May 12, 2026, 7:16 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a2f01468ec08190a320bd3add23a632 |
completed | June 14, 2026, 7:30 p.m. |
| PD | Predicate disambiguation | batch_6a0379eaa540819095a1c5d9f3513f9b |
completed | May 12, 2026, 7:05 p.m. |
Created at: May 1, 2026, 12:31 a.m.