Triple
T13358512
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | UFC 100 |
E318758
|
entity |
| Predicate | payPerViewBuysApprox |
P76559
|
FINISHED |
| Object | 1.6 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: 1.6 million | Statement: [UFC 100, payPerViewBuysApprox, 1.6 million]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: payPerViewBuysApprox Context triple: [UFC 100, payPerViewBuysApprox, 1.6 million]
-
A.
payPerView
Indicates a relationship where access to specific content or an event is granted only upon a one-time payment for that individual viewing.
-
B.
payPerViewDraw
chosen
Indicates that an entity attracts or generates audience interest and revenue specifically through pay-per-view events.
-
C.
commercialCostPer30SecondsUSD
Indicates the monetary cost, in U.S. dollars, to run a 30-second commercial.
-
D.
revenuePaidTo
Indicates that a specified amount of revenue is paid or transferred from one entity to another as a recipient.
-
E.
purchasePrice
Indicates the monetary amount paid or agreed to be paid to acquire something in a purchase transaction.
- 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_69d806b7bbac8190b85278c87fa7aff3 |
completed | April 9, 2026, 8:06 p.m. |
| NER | Named-entity recognition | batch_69da62887e588190bd7241c720a112a2 |
completed | April 11, 2026, 3:02 p.m. |
| PD | Predicate disambiguation | batch_69d9a02c9abc8190b328e7bae747bfc5 |
completed | April 11, 2026, 1:13 a.m. |
Created at: April 9, 2026, 9:32 p.m.