Triple
T21772051
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | North American A-5 Vigilante |
E537457
|
entity |
| Predicate | primaryVariantRole |
P134117
|
FINISHED |
| Object | RA-5C reconnaissance |
—
|
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: RA-5C reconnaissance | Statement: [North American A-5 Vigilante, primaryVariantRole, RA-5C reconnaissance]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: primaryVariantRole Context triple: [North American A-5 Vigilante, primaryVariantRole, RA-5C reconnaissance]
-
A.
primaryVariant
Indicates that one entity is the main or canonical version among multiple related variants of another entity.
-
B.
principalRoleIn
chosen
Indicates that an entity holds the primary or leading role in a particular context, activity, or relationship.
-
C.
primaryParticipant
Indicates that an entity plays the main or most central role in a given event, activity, or relationship.
-
D.
primaryVariantInService
Indicates that a particular variant is the main or default version currently active or in use within a given service or system.
-
E.
primaryVariants
Indicates that one entity is a primary or canonical variant of another, typically within a set of related or alternative forms.
- 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_69e0c470759c819094a215757113562b |
completed | April 16, 2026, 11:13 a.m. |
| NER | Named-entity recognition | batch_69f031af6a488190a2dcebed43d199d4 |
completed | April 28, 2026, 4:03 a.m. |
| PD | Predicate disambiguation | batch_69e6be6299988190a34c98fa76d94700 |
completed | April 21, 2026, 12:01 a.m. |
Created at: April 16, 2026, 6:51 p.m.