Triple
T1502224
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Super Bowl XLVIII |
E33819
|
entity |
| Predicate | USTelevisionViewers |
P2638
|
FINISHED |
| Object | 111.5 million |
—
|
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: 111.5 million | Statement: [Super Bowl XLVIII, USTelevisionViewers, 111.5 million]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: USTelevisionViewers Context triple: [Super Bowl XLVIII, USTelevisionViewers, 111.5 million]
-
A.
USViewers
chosen
Indicates the number or set of viewers located in the United States who watched or were exposed to a particular piece of content or event.
-
B.
televisionExposureLevel
Indicates the degree or amount of exposure an entity has to television content.
-
C.
mediaSignal
Indicates that one entity serves as a medium or channel through which a signal, message, or information is transmitted from a source to a receiver.
-
D.
viewershipRegion
Indicates the geographic region or area in which content is viewed or for which its audience is measured.
-
E.
televisionPartnerUS
Indicates a partnership relationship where one entity serves as the U.S. television partner or broadcaster for another entity’s content or events.
- 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_69a885f352a4819099b24ff15489dede |
completed | March 4, 2026, 7:20 p.m. |
| NER | Named-entity recognition | batch_69a90584b8b881908e112c7e59163812 |
completed | March 5, 2026, 4:24 a.m. |
| PD | Predicate disambiguation | batch_69a88727ce48819089b482cdc25453d1 |
completed | March 4, 2026, 7:25 p.m. |
Created at: March 4, 2026, 7:24 p.m.