Triple
T28313374
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Caucasus front of the Crimean War |
E714062
|
entity |
| Predicate | hasSubconflict |
P130132
|
FINISHED |
| Object | Siege of Kars |
—
|
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: Siege of Kars | Statement: [Caucasus front of the Crimean War, hasSubconflict, Siege of Kars]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasSubconflict Context triple: [Caucasus front of the Crimean War, hasSubconflict, Siege of Kars]
-
A.
hasPartOfConflict
Indicates that one conflict includes another conflict as a constituent or subordinate part of it.
-
B.
notableSubconflict
Indicates that one conflict is a significant, distinguishable component or episode within a larger overarching conflict.
-
C.
subConflict
chosen
Indicates that one conflict is a component, phase, or subordinate part of a larger overarching conflict.
-
D.
hasCauseOfConflict
Indicates a relationship where one entity is the source or reason for a conflict involving another entity.
-
E.
conflictSubcampaign
Indicates that one subcampaign is in conflict with another, such that they cannot or should not run simultaneously or under the same conditions.
- 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_69efb5256afc8190b9322d25c3ae6320 |
completed | April 27, 2026, 7:12 p.m. |
| NER | Named-entity recognition | batch_69fd2839880c819099a7a89783f2270e |
completed | May 8, 2026, 12:03 a.m. |
| PD | Predicate disambiguation | batch_69fd23dc5da48190ae8ba08947d34956 |
completed | May 7, 2026, 11:44 p.m. |
Created at: April 27, 2026, 11:41 p.m.