Triple
T27776366
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Let It Shine |
E699195
|
entity |
| Predicate | hasCastingStage |
P150135
|
FINISHED |
| Object | auditions |
—
|
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: auditions | Statement: [Let It Shine, hasCastingStage, auditions]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasCastingStage Context triple: [Let It Shine, hasCastingStage, auditions]
-
A.
hasCasting
Indicates that an entity features a particular actor or set of actors in its cast.
-
B.
hasStageIn
chosen
Indicates a relationship where one entity occurs, exists, or takes place within a particular stage or phase of another process, lifecycle, or sequence.
-
C.
hasCast
Indicates that a creative work features a particular group of performers or actors.
-
D.
hasStageProduction
Indicates that one entity is realized, adapted, or presented as a stage production (such as a play, musical, or theatrical performance) associated with another entity.
-
E.
isCastingCategoryFor
Indicates that one entity serves as the casting category or type classification used to group or select another entity in a casting context.
- 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_69ef6a4b5a9081909c9111396c2be3d2 |
completed | April 27, 2026, 1:53 p.m. |
| NER | Named-entity recognition | batch_69f7bbf906d8819099020e548dd56bc9 |
completed | May 3, 2026, 9:19 p.m. |
| PD | Predicate disambiguation | batch_69f7b9a2dcf88190a7c9e109e41267be |
completed | May 3, 2026, 9:09 p.m. |
Created at: April 27, 2026, 5:06 p.m.