Triple
T23314101
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mingrelian Affair |
E590656
|
entity |
| Predicate | mainTargets |
P815
|
FINISHED |
| Object | Mingrelian Communist officials |
—
|
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: Mingrelian Communist officials | Statement: [Mingrelian Affair, mainTargets, Mingrelian Communist officials]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: mainTargets Context triple: [Mingrelian Affair, mainTargets, Mingrelian Communist officials]
-
A.
primaryTarget
chosen
Indicates that an entity is the main or most important target of another entity’s action, focus, or effect.
-
B.
intendedTargets
Indicates that an action, message, or object is specifically directed toward or meant to affect particular target entities.
-
C.
primaryTargetType
Indicates the main category or type of entity that is the principal focus or intended recipient of an action, effect, or operation.
-
D.
targetsUseCase
Indicates that one entity is aimed at or designed to address a particular use case associated with another entity.
-
E.
secondaryTarget
Indicates that an entity serves as an additional or subordinate target in relation to a primary target within a given context or action.
- 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_69e25d1d32188190948eb76909d1dcc3 |
completed | April 17, 2026, 4:17 p.m. |
| NER | Named-entity recognition | batch_69f1977ee5d08190a9519d7867d6bef9 |
completed | April 29, 2026, 5:30 a.m. |
| PD | Predicate disambiguation | batch_69effcf8ca2c8190887d4f4656617d21 |
completed | April 28, 2026, 12:19 a.m. |
Created at: April 17, 2026, 5:06 p.m.