Triple
T423249
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Super Bowl LIII |
E8149
|
entity |
| Predicate | USViewersAverage |
P2638
|
FINISHED |
| Object | approximately 98.2 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: approximately 98.2 million | Statement: [Super Bowl LIII, USViewersAverage, approximately 98.2 million]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: USViewersAverage Context triple: [Super Bowl LIII, USViewersAverage, approximately 98.2 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.
broadcastRatingUS
Indicates the television content rating assigned to a broadcast in the United States.
-
C.
televisionExposureLevel
Indicates the degree or amount of exposure an entity has to television content.
-
D.
approximateAudienceSize
Indicates an estimated number of individuals or entities that are expected to be reached or affected in a given context.
-
E.
typicalAudience
Indicates the group of people for whom something (such as a work, product, or resource) is primarily intended or most suitable.
- 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_69a2e7f1d1bc81909cf2dc9754a3c334 |
completed | Feb. 28, 2026, 1:04 p.m. |
| NER | Named-entity recognition | batch_69a2eec200648190bcb9f1b98c8e9cdf |
completed | Feb. 28, 2026, 1:33 p.m. |
| PD | Predicate disambiguation | batch_69a2edd5439c8190aea661b8b4aa51e9 |
completed | Feb. 28, 2026, 1:29 p.m. |
Created at: Feb. 28, 2026, 1:11 p.m.