Triple
T2035555
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ken Jeong |
E44616
|
entity |
| Predicate | hasRealityTVRole |
P10900
|
FINISHED |
| Object | panelist on The Masked Singer (US) |
—
|
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: panelist on The Masked Singer (US) | Statement: [Ken Jeong, hasRealityTVRole, panelist on The Masked Singer (US)]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasRealityTVRole Context triple: [Ken Jeong, hasRealityTVRole, panelist on The Masked Singer (US)]
-
A.
hasFictionalRole
Indicates that an entity plays or is assigned a specific role within a fictional work or narrative.
-
B.
notableProgramInvolvement
chosen
Indicates that an entity has a significant or distinguished role or participation in a particular program.
-
C.
playedRoleIn
Indicates that an entity performed or assumed a specific role or character within a particular event, production, or context.
-
D.
playedKeyRoleIn
Indicates that an entity had a major, influential, or decisive impact on the occurrence, outcome, or success of another entity or event.
-
E.
alsoKnownFor
Indicates that an entity is additionally recognized or noted for another work, role, achievement, or characteristic beyond its primary association.
- 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_69a889159ec481908f9e4472d9f480c7 |
completed | March 4, 2026, 7:33 p.m. |
| NER | Named-entity recognition | batch_69abb934ff948190acd88d4f587463a4 |
completed | March 7, 2026, 5:35 a.m. |
| PD | Predicate disambiguation | batch_69abb7a8125881909c0cb58b777c1faa |
completed | March 7, 2026, 5:29 a.m. |
Created at: March 4, 2026, 7:39 p.m.