Triple
T33703090
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Linda Flynn-Fletcher |
E863510
|
entity |
| Predicate | stepParentOfProtagonist |
P14092
|
FINISHED |
| Object | Ferb Fletcher |
—
|
NE NERFINISHED |
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: Ferb Fletcher | Statement: [Linda Flynn-Fletcher, stepParentOfProtagonist, Ferb Fletcher]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: stepParentOfProtagonist Context triple: [Linda Flynn-Fletcher, stepParentOfProtagonist, Ferb Fletcher]
-
A.
parentOfProtagonistOf
Indicates that one entity is the parent of the main character (protagonist) of another entity.
-
B.
stepParent
chosen
Indicates a parental relationship where an individual is the spouse or partner of a child's biological or adoptive parent but is not themselves a biological or adoptive parent of that child.
-
C.
hasChildProtagonist
Indicates that the work features a child as its main or central character.
-
D.
hasProtagonistRelationship
Indicates that there exists a central, story-driving relationship involving the protagonist and another entity within a narrative.
-
E.
hasProtagonistFamilyMember
Indicates that a work’s protagonist has a specified individual as a member of their family.
- 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_69f3498844608190bb8f9b14908d2510 |
completed | April 30, 2026, 12:22 p.m. |
| NER | Named-entity recognition | batch_69f6fab0b2dc81908a038256328febc0 |
completed | May 3, 2026, 7:35 a.m. |
| PD | Predicate disambiguation | batch_69f6f96dd4c8819093d6a7bd046a9ad5 |
completed | May 3, 2026, 7:29 a.m. |
Created at: May 1, 2026, 1:43 a.m.