Triple
T24203606
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | AJ Lee |
E600042
|
entity |
| Predicate | onScreenRole |
P124942
|
FINISHED |
| Object | Raw General Manager |
—
|
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: Raw General Manager | Statement: [AJ Lee, onScreenRole, Raw General Manager]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: onScreenRole Context triple: [AJ Lee, onScreenRole, Raw General Manager]
-
A.
onScreenStatus
Indicates that an entity’s current presence or visibility state is being specified relative to a screen or display.
-
B.
onScreenDynamicWith
Indicates that two entities are simultaneously visible and interacting or changing together within the same on-screen context.
-
C.
hasEarlyScreenRole
Indicates that an entity played a role in an early stage of another entity’s screen-based career or production history.
-
D.
hasOnScreenRelative
Indicates that one entity has a family member who appears or is depicted on screen in relation to it.
-
E.
onScreenLeader
chosen
Indicates that an entity serves as the primary or leading figure visibly presented on a screen in a given context or scene.
- 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_69e288ceaab88190899d0acb5931591d |
completed | April 17, 2026, 7:23 p.m. |
| NER | Named-entity recognition | batch_69f27ca38c148190ae65cd692567d43d |
completed | April 29, 2026, 9:48 p.m. |
| PD | Predicate disambiguation | batch_69f1c43e55688190b55fc20274ed471c |
completed | April 29, 2026, 8:41 a.m. |
Created at: April 17, 2026, 11:37 p.m.