Triple
T36368496
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | TaxSlayer Gator Bowl |
E895688
|
entity |
| Predicate | typicalSelectionPool |
P12230
|
FINISHED |
| Object | SEC teams not in the College Football Playoff |
—
|
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: SEC teams not in the College Football Playoff | Statement: [TaxSlayer Gator Bowl, typicalSelectionPool, SEC teams not in the College Football Playoff]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: typicalSelectionPool Context triple: [TaxSlayer Gator Bowl, typicalSelectionPool, SEC teams not in the College Football Playoff]
-
A.
typicalNumberOfSelections
Indicates the usual or expected count of selections made in a given choice or selection process.
-
B.
typicalOption
Indicates that one option is considered standard, common, or most representative among a set of possible options.
-
C.
typicalIn
chosen
Indicates that something commonly occurs, appears, or is found within a given context, category, or environment.
-
D.
typicalCandidate
Indicates that an entity is a standard or representative example of what is usually considered a candidate in a given context.
-
E.
typicalHostSelection
Indicates the usual or preferred choice of host entity that is selected in a given context or process.
- 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_69f76e5115588190ad8738860b7bc68b |
completed | May 3, 2026, 3:48 p.m. |
| NER | Named-entity recognition | batch_6a037c8d06cc8190ab6a5e18d9d2571e |
completed | May 12, 2026, 7:16 p.m. |
| PD | Predicate disambiguation | batch_6a037a0a54cc8190868c1bfa1590d1a6 |
completed | May 12, 2026, 7:05 p.m. |
Created at: May 3, 2026, 4:10 p.m.