Triple
T29742488
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Linda Dufresne |
E752648
|
entity |
| Predicate | relationToProtagonist |
P38921
|
FINISHED |
| Object | wife of central character Andy Dufresne |
—
|
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: wife of central character Andy Dufresne | Statement: [Linda Dufresne, relationToProtagonist, wife of central character Andy Dufresne]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: relationToProtagonist Context triple: [Linda Dufresne, relationToProtagonist, wife of central character Andy Dufresne]
-
A.
relationshipToCharacter
chosen
Indicates the specific type of personal, social, or narrative connection that one entity has to a given character.
-
B.
relationshipToRelative
Indicates the specific familial connection or kinship role that one person has in relation to a particular relative.
-
C.
hasProtagonistRelationship
Indicates that there exists a central, story-driving relationship involving the protagonist and another entity within a narrative.
-
D.
relativeOfMainCharacter
Indicates that one entity is a family member or relative of the main character entity.
-
E.
relationToBabo
Indicates a relationship or connection that an entity has to the person or entity referred to as "Babo."
- 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_69f0d62b064081908c1ae61cd68fb139 |
completed | April 28, 2026, 3:45 p.m. |
| NER | Named-entity recognition | batch_6a01ac8b4ac881908aa52079c985ddac |
completed | May 11, 2026, 10:16 a.m. |
| PD | Predicate disambiguation | batch_6a01aa7fa7b48190b4911aa6bcabe7eb |
completed | May 11, 2026, 10:07 a.m. |
Created at: April 28, 2026, 7:48 p.m.