Triple
T122223
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Power Five |
E2472
|
entity |
| Predicate | televisionRevenueRank |
P1944
|
FINISHED |
| Object | highest among college conferences |
—
|
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: highest among college conferences | Statement: [Power Five, televisionRevenueRank, highest among college conferences]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: televisionRevenueRank Context triple: [Power Five, televisionRevenueRank, highest among college conferences]
-
A.
televisionShow
Indicates that one entity is a television show associated with, or featured in relation to, another entity.
-
B.
televisionExposureLevel
Indicates the degree or amount of exposure an entity has to television content.
-
C.
rankedAs
chosen
Indicates that one entity is assigned a specific position or level in an ordered ranking relative to others.
-
D.
rankedBy
Indicates that one entity is ordered or assigned a position in a hierarchy or list according to criteria determined or applied by another entity.
-
E.
broadcastNetwork
Indicates that one entity serves as the television or radio network that broadcasts the programming or content of another entity.
- 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_69a2506c5428819085c28a8884790e29 |
completed | Feb. 28, 2026, 2:18 a.m. |
| NER | Named-entity recognition | batch_69a2573b4e7481909ee09d2899f8a74b |
completed | Feb. 28, 2026, 2:47 a.m. |
| PD | Predicate disambiguation | batch_69a2564928208190966a619680a0d6e2 |
completed | Feb. 28, 2026, 2:43 a.m. |
Created at: Feb. 28, 2026, 2:24 a.m.