Triple
T29041190
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Super Bowl XLI |
E737999
|
entity |
| Predicate | televisionShareUS |
P72301
|
FINISHED |
| Object | 63 |
—
|
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: 63 | Statement: [Super Bowl XLI, televisionShareUS, 63]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: televisionShareUS Context triple: [Super Bowl XLI, televisionShareUS, 63]
-
A.
televisionShare
chosen
Indicates the proportion of total television audience or viewing time captured by a particular program, channel, or entity relative to all viewing in a given market or period.
-
B.
tvShareUS
Indicates the proportion of television viewership or audience share that occurs within the United States.
-
C.
televisionPartnerUS
Indicates a partnership relationship where one entity serves as the U.S. television partner or broadcaster for another entity’s content or events.
-
D.
televisionActivity
Indicates engaging in activities related to watching, using, or interacting with a television.
-
E.
televisionDivision
Indicates a relationship where an entity functions as the television-focused division or department within a larger organization or company.
- 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_69f077efb3848190b41574e1670f6ae2 |
completed | April 28, 2026, 9:03 a.m. |
| NER | Named-entity recognition | batch_69f66041993c8190877d0d08d57dbac5 |
completed | May 2, 2026, 8:36 p.m. |
| PD | Predicate disambiguation | batch_69f65c2376a08190be5215171e908e69 |
completed | May 2, 2026, 8:18 p.m. |
Created at: April 28, 2026, 10:02 a.m.