Triple
T29040593
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Slam Dunk Ernest |
E737984
|
entity |
| Predicate | franchiseCharacterCreator |
P166540
|
FINISHED |
| Object | John R. Cherry III |
—
|
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: John R. Cherry III | Statement: [Slam Dunk Ernest, franchiseCharacterCreator, John R. Cherry III]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: franchiseCharacterCreator Context triple: [Slam Dunk Ernest, franchiseCharacterCreator, John R. Cherry III]
-
A.
fictionalCharacterFrom
Indicates that a fictional character originates from, or is created within, a particular work, universe, or source.
-
B.
characterGenerator
Indicates a relationship where an entity produces, defines, or initializes characters or character data for use in another context.
-
C.
fictionalCharacterAssisted
Indicates that one fictional character provided help, support, or assistance to another fictional character.
-
D.
franchiseCharacter
Indicates a relationship where a character belongs to, appears in, or is part of a particular media franchise.
-
E.
brandCharacter
Indicates that one entity serves as a brand character or mascot representing another entity (typically a brand or product).
- F. None of above. chosen
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_69f077efb3848190b41574e1670f6ae2 |
completed | April 28, 2026, 9:03 a.m. |
| NER | Named-entity recognition | batch_69f6622808b48190bbabcc75288ab031 |
completed | May 2, 2026, 8:44 p.m. |
| PD | Predicate disambiguation | batch_69f660f082508190a95a7888ad66cb2e |
completed | May 2, 2026, 8:39 p.m. |
| PDg | Predicate description generation | batch_69f6617a7e7c81908cfac4a2250797ee |
completed | May 2, 2026, 8:41 p.m. |
Created at: April 28, 2026, 10:01 a.m.