Triple
T23969028
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 227 |
E604174
|
entity |
| Predicate | featuredPerformerInTheme |
P21830
|
FINISHED |
| Object | Marla Gibbs |
—
|
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: Marla Gibbs | Statement: [227, featuredPerformerInTheme, Marla Gibbs]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: featuredPerformerInTheme Context triple: [227, featuredPerformerInTheme, Marla Gibbs]
-
A.
performedThemeFor
Indicates that an agent carried out or executed a performance specifically for a particular theme or subject.
-
B.
performerInShow
Indicates that an entity participates as a performer in a particular show or performance.
-
C.
openingThemePerformer
chosen
Indicates the performer or group responsible for performing the opening theme of a work (such as a TV show, film, or game).
-
D.
featuresPerformerCameo
Indicates that the subject includes a brief, special appearance by a performer who is not part of the main cast or lineup.
-
E.
endThemePerformer
Indicates that an entity performs or is responsible for the concluding or final theme in a work or event.
- 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_69e29543019c8190872462e593cc50b4 |
completed | April 17, 2026, 8:17 p.m. |
| NER | Named-entity recognition | batch_69f1d1da2ab08190bfe653fb5a9f2c96 |
completed | April 29, 2026, 9:39 a.m. |
| PD | Predicate disambiguation | batch_69f161578d54819084a8b35496299993 |
completed | April 29, 2026, 1:39 a.m. |
Created at: April 17, 2026, 9:25 p.m.