Triple
T24322607
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Russia and Prussia |
E613008
|
entity |
| Predicate | wereSignatoriesOf |
P63848
|
FINISHED |
| Object | various coalition treaties against France |
—
|
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: various coalition treaties against France | Statement: [Russia and Prussia, wereSignatoriesOf, various coalition treaties against France]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: wereSignatoriesOf Context triple: [Russia and Prussia, wereSignatoriesOf, various coalition treaties against France]
-
A.
wasSignatoryOf
chosen
Indicates that an entity formally signed or endorsed a specific document, agreement, or treaty as a participating party.
-
B.
foundingSignatory
Indicates that an entity was an original signer or member at the founding of another entity, agreement, or organization.
-
C.
treatySignedWith
Indicates that a formal treaty or agreement has been officially signed between two parties.
-
D.
signedTreatyAt
Indicates that an entity formally entered into and endorsed a treaty at a specific location.
-
E.
treatySignedFor
Indicates that a formal treaty has been signed on behalf of, or in representation of, a particular entity, cause, or subject.
- 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_69e2d7da491c8190b6e6218af50923db |
completed | April 18, 2026, 1:01 a.m. |
| NER | Named-entity recognition | batch_69f292ad4cc881908794b501cf70b7a1 |
completed | April 29, 2026, 11:22 p.m. |
| PD | Predicate disambiguation | batch_69f1c45f45888190a9ccc225906c34bd |
completed | April 29, 2026, 8:42 a.m. |
Created at: April 18, 2026, 1:52 a.m.