Triple
T37470781
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Niya |
E931145
|
entity |
| Predicate | supportsClassRoles |
P32439
|
FINISHED |
| Object | tanks |
—
|
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: tanks | Statement: [Niya, supportsClassRoles, tanks]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: supportsClassRoles Context triple: [Niya, supportsClassRoles, tanks]
-
A.
supportedClass
chosen
Indicates that one entity is a class or type that is recognized, handled, or operable within the capabilities or context provided by another entity.
-
B.
supportsRole
Indicates that one entity provides the necessary functionality, resources, or conditions for another entity to perform or occupy a specific role.
-
C.
supportsClassification
Indicates that one entity provides the capability or functionality needed for another entity to perform or maintain a specific classification.
-
D.
supportsClassificationUpTo
Indicates that one entity provides assistance, resources, or functionality enabling another entity to perform classification tasks up to a specified level, scope, or complexity.
-
E.
includesRoles
Indicates that one entity contains or encompasses one or more specified roles within its scope or structure.
- 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_69f76ec2af148190897d101070d7f415 |
completed | May 3, 2026, 3:50 p.m. |
| NER | Named-entity recognition | batch_6a037c8efcd4819088c2aeead65d93df |
completed | May 12, 2026, 7:16 p.m. |
| PD | Predicate disambiguation | batch_6a037a13a1308190a202df66f4781855 |
completed | May 12, 2026, 7:05 p.m. |
Created at: May 3, 2026, 4:17 p.m.