Triple
T26675522
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Castillo vs. Mayweather I |
E672443
|
entity |
| Predicate | undercardType |
P5430
|
FINISHED |
| Object | pay-per-view undercard and main event card |
—
|
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: pay-per-view undercard and main event card | Statement: [Castillo vs. Mayweather I, undercardType, pay-per-view undercard and main event card]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: undercardType Context triple: [Castillo vs. Mayweather I, undercardType, pay-per-view undercard and main event card]
-
A.
cardType
chosen
Indicates the classification or category assigned to a card within a given system or context.
-
B.
undercard
Indicates that one event, match, or performance is scheduled to occur before and in support of a main or headline event within the same program or card.
-
C.
cardFormat
Indicates the specific layout or structural style in which a card or card-like item is presented or encoded.
-
D.
cardRequiredFor
Indicates that a specific card must be presented or possessed in order to access, use, or complete the related item, service, or action.
-
E.
cardVariant
Indicates that one card is a specific version or variation of another base card.
- 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_69eecda13424819092b17942c4edf722 |
completed | April 27, 2026, 2:44 a.m. |
| NER | Named-entity recognition | batch_69f69edbb7648190bd89c57e0932eac1 |
completed | May 3, 2026, 1:03 a.m. |
| PD | Predicate disambiguation | batch_69f69d17e8d48190b30bcc2f4bd81eb2 |
completed | May 3, 2026, 12:55 a.m. |
Created at: April 27, 2026, 3:16 a.m.