Triple
T38312656
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | UFC 90 |
E1033734
|
entity |
| Predicate | mainEventFighter |
P101800
|
FINISHED |
| Object | Anderson Silva |
—
|
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: Anderson Silva | Statement: [UFC 90, mainEventFighter, Anderson Silva]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: mainEventFighter Context triple: [UFC 90, mainEventFighter, Anderson Silva]
-
A.
hasFighter
Indicates that an entity possesses, controls, or is associated with a fighter (such as a combatant, combat vehicle, or fighting unit).
-
B.
primaryFighterModel
Indicates that one entity is the main or standard fighter aircraft model associated with another entity (such as a country, air force, or military unit).
-
C.
mainCombatant
Indicates that the subject is the primary participant or leading party in a conflict, battle, or combat situation involving the object.
-
D.
hasFight
Indicates that one entity engages in a physical or verbal conflict with another entity.
-
E.
featuredFighter
chosen
Indicates that a particular fighter is highlighted or prominently showcased in a given context or 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_69f76e132c408190969b3d35c04b87ae |
completed | May 3, 2026, 3:47 p.m. |
| NER | Named-entity recognition | batch_69fccbd826708190b5fab12c4236299a |
completed | May 7, 2026, 5:28 p.m. |
| PD | Predicate disambiguation | batch_69fcc58838e08190b8fa54aa5c165f2d |
completed | May 7, 2026, 5:02 p.m. |
Created at: May 3, 2026, 4:30 p.m.