Triple
T4534131
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Treaty of Adrianople (1829) |
E106364
|
entity |
| Predicate | openedStraitsTo |
P4864
|
FINISHED |
| Object | Russian merchant ships |
—
|
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: Russian merchant ships | Statement: [Treaty of Adrianople (1829), openedStraitsTo, Russian merchant ships]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: openedStraitsTo Context triple: [Treaty of Adrianople (1829), openedStraitsTo, Russian merchant ships]
-
A.
seaRouteOpened
Indicates that a maritime route between locations has been established and made available for use.
-
B.
openedAsEmbassy
Indicates that a diplomatic mission or office was formally inaugurated and began operating with the status of an embassy.
-
C.
hasStrait
Indicates that there is a strait—a narrow body of water—connecting or lying between the two referenced geographic entities.
-
D.
opens
chosen
Indicates that one entity causes or allows another entity (such as an object, space, or resource) to become accessible or no longer closed.
-
E.
opened
Indicates that one entity caused another entity (such as an object, container, or passage) to change from a closed or inaccessible state to an open or accessible state.
- 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_69bd43f3d6e08190a91824f833d51bbe |
completed | March 20, 2026, 12:56 p.m. |
| NER | Named-entity recognition | batch_69bd57a2301c8190aa59280a16750156 |
completed | March 20, 2026, 2:20 p.m. |
| PD | Predicate disambiguation | batch_69bd521edd00819099dfccaa65dddd61 |
completed | March 20, 2026, 1:56 p.m. |
Created at: March 20, 2026, 1:04 p.m.