Triple
T31448566
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kitri |
E802254
|
entity |
| Predicate | trainingLevelRequired |
P56693
|
FINISHED |
| Object | principal ballerina |
—
|
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: principal ballerina | Statement: [Kitri, trainingLevelRequired, principal ballerina]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: trainingLevelRequired Context triple: [Kitri, trainingLevelRequired, principal ballerina]
-
A.
trainingLevel
Indicates the degree or stage of training or skill development that an entity has attained.
-
B.
requiresSkillLevel
chosen
Indicates that performing or engaging in something depends on possessing at least a specified level of skill.
-
C.
qualificationLevel
Indicates the degree or rank of competence, certification, or formal credentials required for or possessed in relation to something.
-
D.
certificationLevel
Indicates the specific rank or degree of formal qualification or authorization that an entity has achieved within a defined certification system.
-
E.
disciplineLevel
Indicates the degree or strictness of control, order, or self-regulation applied in a given context or relationship.
- 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_69f348c5a6bc819092a557e95438976f |
completed | April 30, 2026, 12:19 p.m. |
| NER | Named-entity recognition | batch_69f6d16f5cb881908eed141afaaa0b51 |
completed | May 3, 2026, 4:39 a.m. |
| PD | Predicate disambiguation | batch_69f6cfe45554819089cbbd538d992132 |
completed | May 3, 2026, 4:32 a.m. |
Created at: April 30, 2026, 9:11 p.m.