Triple
T34931164
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ukrainian Navy gunboat Berdyansk |
E1007437
|
entity |
| Predicate | incidentCounterparty |
P113889
|
FINISHED |
| Object | Russian Coast Guard |
—
|
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: Russian Coast Guard | Statement: [Ukrainian Navy gunboat Berdyansk, incidentCounterparty, Russian Coast Guard]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: incidentCounterparty Context triple: [Ukrainian Navy gunboat Berdyansk, incidentCounterparty, Russian Coast Guard]
-
A.
collisionCounterpartyFlagState
Indicates whether an entity is flagged as the counterparty involved in a collision event and the status of that flag.
-
B.
transactionCounterparty
Indicates that one entity is the other party involved in a financial or commercial transaction with the subject entity.
-
C.
counterpartService
Indicates that one service functions as the corresponding or matching service to another within a defined relationship or context.
-
D.
incidentWith
chosen
Indicates that one entity is involved in, affected by, or associated with a particular incident or event together with another entity.
-
E.
counterpartyCountry
Indicates the country associated with the other party involved in a transaction, agreement, 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_69f76dc3d83881909d5c3c14455cfa2c |
completed | May 3, 2026, 3:46 p.m. |
| NER | Named-entity recognition | batch_69f782c98fa08190870b68de2c1ff26a |
completed | May 3, 2026, 5:15 p.m. |
| PD | Predicate disambiguation | batch_69f781020cc4819088c40cb8589504e4 |
completed | May 3, 2026, 5:08 p.m. |
Created at: May 3, 2026, 4 p.m.