Triple
T34804062
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | UFC 257 |
E1003299
|
entity |
| Predicate | mainEventPreviousMeetingWeightClass |
P8068
|
FINISHED |
| Object | featherweight |
—
|
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: featherweight | Statement: [UFC 257, mainEventPreviousMeetingWeightClass, featherweight]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: mainEventPreviousMeetingWeightClass Context triple: [UFC 257, mainEventPreviousMeetingWeightClass, featherweight]
-
A.
mainEventPreviousMeetingLoser
Indicates that the referenced entity is the loser of the previous meeting between the participants in the main event.
-
B.
performedByWeightClass
Indicates that an action or event is carried out by an entity belonging to a specific weight class.
-
C.
heavyweightChampionEnteringEvent
Indicates that a heavyweight champion is entering or participating in a particular event.
-
D.
weightClass
chosen
Indicates the categorical grouping of an entity based on its weight range or mass classification.
-
E.
competesInWeightClass
Indicates that an entity participates in a competition within a specific weight classification or division.
- 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_69f76db543808190b188c6c86a91491b |
completed | May 3, 2026, 3:45 p.m. |
| NER | Named-entity recognition | batch_69f78c61ed4c8190ad84c918fa9af55a |
completed | May 3, 2026, 5:56 p.m. |
| PD | Predicate disambiguation | batch_69f78b8cb3a881909ebaac1b503988c2 |
completed | May 3, 2026, 5:53 p.m. |
Created at: May 3, 2026, 3:59 p.m.