Triple
T34857989
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | fronts of the Red Army |
E1004777
|
entity |
| Predicate | higherUnitOf |
P89327
|
FINISHED |
| Object | Soviet field army |
—
|
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: Soviet field army | Statement: [fronts of the Red Army, higherUnitOf, Soviet field army]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: higherUnitOf Context triple: [fronts of the Red Army, higherUnitOf, Soviet field army]
-
A.
superunitOf
chosen
Indicates that one unit is hierarchically above and directly encompasses another unit within an organizational or structural system.
-
B.
higherDenomination
Indicates that one entity represents a monetary value that is greater than the monetary value represented by another entity.
-
C.
raisedUnit
Indicates that one entity has increased the level, amount, or status of another entity, often in a measurable or unit-based sense.
-
D.
isMajorUnitOf
Indicates that one unit functions as the primary or principal component within a larger organizational or structural context of another entity.
-
E.
higherTierAlternative
Indicates that one option serves as a superior or more advanced alternative to another within a tiered structure.
- 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_69f76dba76f0819090643cba102c41ec |
completed | May 3, 2026, 3:46 p.m. |
| NER | Named-entity recognition | batch_69fd592e48cc81909d754cc6c4bd99ae |
completed | May 8, 2026, 3:31 a.m. |
| PD | Predicate disambiguation | batch_69fd58b7f9b881909dc099b28d567784 |
completed | May 8, 2026, 3:30 a.m. |
Created at: May 3, 2026, 4 p.m.