Triple
T31630364
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Daytime Emmy Award for Outstanding Morning Program |
E807145
|
entity |
| Predicate | hasAwardedForProgram |
P2391
|
FINISHED |
| Object | Good Morning America |
—
|
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: Good Morning America | Statement: [Daytime Emmy Award for Outstanding Morning Program, hasAwardedForProgram, Good Morning America]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasAwardedForProgram Context triple: [Daytime Emmy Award for Outstanding Morning Program, hasAwardedForProgram, Good Morning America]
-
A.
hasAwarded
chosen
Indicates that one entity has given or conferred an award to another entity.
-
B.
hasAwardProgram
Indicates that an entity maintains or offers a formal award or recognition program.
-
C.
isAwardedWithin
Indicates that an award or recognition is granted to an entity within a specified context, scope, or time frame.
-
D.
hasAwardUnit
Indicates that an award is associated with, measured in, or granted in terms of a specific unit (such as a quantity, category, or subdivision).
-
E.
hasAwardedPerformanceBy
Indicates that an award or recognition has been given to a performance by a specific entity (such as a person or organization).
- 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_69f348d892948190915f8facacb9568c |
completed | April 30, 2026, 12:19 p.m. |
| NER | Named-entity recognition | batch_69f6a8e476508190824926d579f52ff6 |
completed | May 3, 2026, 1:46 a.m. |
| PD | Predicate disambiguation | batch_69f6a757c6e081908e37631e5d8d246b |
completed | May 3, 2026, 1:39 a.m. |
Created at: April 30, 2026, 10:45 p.m.