Triple
T3926932
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | College Football on CBS |
E93297
|
entity |
| Predicate | typicalKickoffSlot |
P51718
|
FINISHED |
| Object | Saturday afternoon |
—
|
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: Saturday afternoon | Statement: [College Football on CBS, typicalKickoffSlot, Saturday afternoon]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: typicalKickoffSlot Context triple: [College Football on CBS, typicalKickoffSlot, Saturday afternoon]
-
A.
penaltyShootOutLocation
Indicates the specific place or venue where a penalty shoot-out event occurs.
-
B.
gameWinningKicker
Indicates that an entity serves as the kicker responsible for securing the decisive, game-winning score in a contest.
-
C.
typicalFormation
Indicates the usual or characteristic way in which something is formed, structured, or comes into existence.
-
D.
typicalOpeningPattern
Indicates that there is a commonly occurring or characteristic initial configuration, sequence, or arrangement associated with the given context.
-
E.
typicalGameLocation
Indicates the usual or characteristic place where a game is played or takes place.
- F. None of above. chosen
Provenance (4 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_69aed96bfa1081908f7b30f2c647dee6 |
completed | March 9, 2026, 2:30 p.m. |
| NER | Named-entity recognition | batch_69aeed80a1e48190aa39748b9db42701 |
completed | March 9, 2026, 3:55 p.m. |
| PD | Predicate disambiguation | batch_69aee7609c4081908000ce12ae827c3f |
completed | March 9, 2026, 3:29 p.m. |
| PDg | Predicate description generation | batch_69aeeb5f859c819095b61f5ba8eace4f |
completed | March 9, 2026, 3:46 p.m. |
Created at: March 9, 2026, 3:23 p.m.