Triple
T23684595
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | UFC 239 |
E585127
|
entity |
| Predicate | coMainEventMethod |
P153377
|
FINISHED |
| Object | head kick and punches TKO |
—
|
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: head kick and punches TKO | Statement: [UFC 239, coMainEventMethod, head kick and punches TKO]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: coMainEventMethod Context triple: [UFC 239, coMainEventMethod, head kick and punches TKO]
-
A.
coMainEvent
Indicates that two or more events share equal primary status as the main featured events within the same program or occasion.
-
B.
methodMainEvent
Indicates that an event is the primary or main event associated with a particular method.
-
C.
mainEventClass
Indicates that an event is classified as the primary or most central event within a given context or dataset.
-
D.
mainEventFor
Indicates that one event is the primary or central event associated with another entity, such as a context, grouping, or larger occurrence.
-
E.
coMainEventWinner
Indicates that an entity is one of the winners of a shared or jointly headlined main event.
- F. None of above. chosen
Provenance (4 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_69e249037ce0819088b149608e98f685 |
completed | April 17, 2026, 2:51 p.m. |
| NER | Named-entity recognition | batch_69f1b4fb26c88190a6776e4dfd10d54c |
completed | April 29, 2026, 7:36 a.m. |
| PD | Predicate disambiguation | batch_69f155d5265881908e43a9696b6a6d0f |
completed | April 29, 2026, 12:50 a.m. |
| PDg | Predicate description generation | batch_69f157cc43a881909ed2d8b0a09b5d73 |
completed | April 29, 2026, 12:58 a.m. |
Created at: April 17, 2026, 6:52 p.m.