Triple
T35527246
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | IBJJF Brazilian jiu-jitsu competitions |
E1026704
|
entity |
| Predicate | includeBeltLevel |
P148255
|
FINISHED |
| Object | white belt |
—
|
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: white belt | Statement: [IBJJF Brazilian jiu-jitsu competitions, includeBeltLevel, white belt]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: includeBeltLevel Context triple: [IBJJF Brazilian jiu-jitsu competitions, includeBeltLevel, white belt]
-
A.
includesVehicleLevel
Indicates that something encompasses or applies to a specific level or category associated with a vehicle.
-
B.
includesClubLevel
Indicates that one entity encompasses or provides access to a specific club-level tier, area, or privileges associated with another entity.
-
C.
includeSkillLevel
chosen
Indicates that a specified skill is associated with an entity together with a particular proficiency or mastery level.
-
D.
raidTierItemLevelContext
Indicates the item-level context or scaling tier associated with items obtained from a raid.
-
E.
coversLevel
Indicates that one entity includes or encompasses a particular level or layer of another entity or system.
- 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_69f76dff7e508190b28ceeee770dce23 |
completed | May 3, 2026, 3:47 p.m. |
| NER | Named-entity recognition | batch_6a037c8d06cc8190ab6a5e18d9d2571e |
completed | May 12, 2026, 7:16 p.m. |
| PD | Predicate disambiguation | batch_6a037a04d8348190a4819666eab42c9b |
completed | May 12, 2026, 7:05 p.m. |
Created at: May 3, 2026, 4:04 p.m.