Triple
T31214744
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | siege of Novgorod (1611) |
E795839
|
entity |
| Predicate | hasConflictSide |
P203736
|
FINISHED |
| Object | Swedish side |
—
|
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: Swedish side | Statement: [siege of Novgorod (1611), hasConflictSide, Swedish side]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasConflictSide Context triple: [siege of Novgorod (1611), hasConflictSide, Swedish side]
-
A.
hasConflictStatus
Indicates that there exists a state of conflict or dispute associated with the relationship between the involved entities.
-
B.
hasConflictScale
Indicates the degree or intensity of conflict present in a given relationship, situation, or interaction.
-
C.
hasConflictCause
Indicates that one entity is the cause or source of a conflict involving another entity.
-
D.
hasRelatedConflict
Indicates that one entity is associated with another entity through a related or connected conflict, dispute, or incompatibility.
-
E.
hasOngoingConflict
Indicates that there is a current, unresolved state of opposition, dispute, or hostilities between the related entities.
- 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_69f224d9d52c8190a61f68ded37fa755 |
completed | April 29, 2026, 3:33 p.m. |
| NER | Named-entity recognition | batch_6a01d7b3ce8c8190b2f90be730505765 |
completed | May 11, 2026, 1:20 p.m. |
| PD | Predicate disambiguation | batch_6a01d5115a6c8190a6d9f96ec484135a |
completed | May 11, 2026, 1:09 p.m. |
| PDg | Predicate description generation | batch_6a01d7b312908190bae3320b9c206cae |
completed | May 11, 2026, 1:20 p.m. |
Created at: April 29, 2026, 9:10 p.m.