Triple
T20004786
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Joe Kelly |
E494425
|
entity |
| Predicate | basedOnCharacterOrigin |
P138323
|
FINISHED |
| Object | NBC Sports Premier League promos |
—
|
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: NBC Sports Premier League promos | Statement: [Joe Kelly, basedOnCharacterOrigin, NBC Sports Premier League promos]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: basedOnCharacterOrigin Context triple: [Joe Kelly, basedOnCharacterOrigin, NBC Sports Premier League promos]
-
A.
characterOrigin
Indicates the source, background, or initial context from which a character originates.
-
B.
basedOnCharacterBy
Indicates that one work, adaptation, or portrayal is derived from or inspired by a character created by another entity.
-
C.
basedOnCharacterFromWork
Indicates that one entity is derived from, inspired by, or modeled after a character that appears in another creative work.
-
D.
originOfCharacter
Indicates the source or place from which a character originates or is created.
-
E.
hasMultipleCharacterOrigins
Indicates that an entity is associated with more than one origin story or background for a character.
- 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_69da626b2d748190886981ea90c8b2ea |
completed | April 11, 2026, 3:02 p.m. |
| NER | Named-entity recognition | batch_69e661a46c748190a141ab5aac6ea250 |
completed | April 20, 2026, 5:25 p.m. |
| PD | Predicate disambiguation | batch_69e54cdddbd48190becc8b2aa5ab4ef9 |
completed | April 19, 2026, 9:45 p.m. |
| PDg | Predicate description generation | batch_69e54fc20888819083c9118a09d0d2dc |
completed | April 19, 2026, 9:57 p.m. |
Created at: April 11, 2026, 3:33 p.m.