Triple
T34804059
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | UFC 257 |
E1003299
|
entity |
| Predicate | mainEventPreviousMeetingEvent |
P42309
|
FINISHED |
| Object | UFC 178 |
—
|
NE NERFINISHED |
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: UFC 178 | Statement: [UFC 257, mainEventPreviousMeetingEvent, UFC 178]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: mainEventPreviousMeetingEvent Context triple: [UFC 257, mainEventPreviousMeetingEvent, UFC 178]
-
A.
eventBefore
chosen
Indicates that one event occurs earlier in time than another event.
-
B.
previouslyConveneAt
Indicates that an entity held or participated in a gathering, meeting, or session at a specified location or venue at some earlier time.
-
C.
previousMeetingPlace
Indicates the location where two or more entities met on a prior occasion.
-
D.
plannedBeforeEvent
Indicates that one event or action was planned or scheduled to occur prior to a specified reference event.
-
E.
meetsForEvent
Indicates that two or more entities come together at the same place and time specifically to participate in a particular event.
- 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_69f77a8cf978819086a26dbbbd31d9a2 |
completed | May 3, 2026, 4:40 p.m. |
| PD | Predicate disambiguation | batch_69f7795b1abc8190823664d1caa94649 |
completed | May 3, 2026, 4:35 p.m. |
Created at: May 3, 2026, 3:59 p.m.