Triple
T22917412
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Zane Frazier |
E568769
|
entity |
| Predicate | foughtUnderRuleset |
P139106
|
FINISHED |
| Object | early UFC rules |
—
|
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: early UFC rules | Statement: [Zane Frazier, foughtUnderRuleset, early UFC rules]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: foughtUnderRuleset Context triple: [Zane Frazier, foughtUnderRuleset, early UFC rules]
-
A.
playedUnderRulesOf
Indicates that an activity or game was conducted in accordance with a specified set of rules or regulations.
-
B.
battleDuringRule
Indicates that a battle or military conflict occurred during the period when a particular entity (typically a ruler or regime) held power.
-
C.
hasBattleFormat
chosen
Indicates that an entity is associated with, or conducted under, a particular battle or combat ruleset or format.
-
D.
wasBattlegroundRace
Indicates that a particular race or ethnic group was a primary party or side in a conflict or struggle over control, influence, or dominance in a given context.
-
E.
hasRulebook
Indicates that one entity possesses, is governed by, or is associated with a specific rulebook.
- 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_69e2458d90c88190a58cead4e781ca6a |
completed | April 17, 2026, 2:37 p.m. |
| NER | Named-entity recognition | batch_69f1807a14648190b5d5f7d926f19320 |
completed | April 29, 2026, 3:52 a.m. |
| PD | Predicate disambiguation | batch_69ef3b7c5fc081909ac50c5c8569cc19 |
completed | April 27, 2026, 10:33 a.m. |
Created at: April 17, 2026, 3:42 p.m.