Triple
T32919558
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Typhoon |
E842106
|
entity |
| Predicate | classificationByRussia |
P176992
|
FINISHED |
| Object | Akula-class |
—
|
NE NERFINISHED |
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: Akula-class | Statement: [Typhoon, classificationByRussia, Akula-class]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: classificationByRussia Context triple: [Typhoon, classificationByRussia, Akula-class]
-
A.
classificationByUSSR
Indicates that an entity is categorized or designated according to a classification system used by the USSR.
-
B.
legalStatusClaimedByRussia
Indicates that Russia asserts a particular legal status or claim over the referenced entity or territory.
-
C.
RussiaControls
Indicates that Russia exercises authority, influence, or governing power over the specified entity or territory.
-
D.
viewsRussiaAs
Indicates that one entity regards, perceives, or characterizes Russia in a particular way (e.g., as a friend, enemy, threat, or partner).
-
E.
stationingConsideredByRussia
Indicates that the deployment or positioning of something (e.g., forces, equipment, or assets) is regarded, evaluated, or treated in a particular way by Russia.
- F. None of above. chosen
Provenance (4 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_69f3494779388190a5d3e97f92278be2 |
completed | April 30, 2026, 12:21 p.m. |
| NER | Named-entity recognition | batch_69f6f85bfba48190aba95b40642a8ca7 |
completed | May 3, 2026, 7:25 a.m. |
| PD | Predicate disambiguation | batch_69f6f6619404819084662aef1238261c |
completed | May 3, 2026, 7:16 a.m. |
| PDg | Predicate description generation | batch_69f6f814fcf48190ae4504154d1b2c05 |
completed | May 3, 2026, 7:24 a.m. |
Created at: May 1, 2026, 1:19 a.m.