Triple
T3708086
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Imperial Russian administrative system |
E80940
|
entity |
| Predicate | topLevelUnit |
P19213
|
FINISHED |
| Object | governorate |
—
|
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: governorate | Statement: [Imperial Russian administrative system, topLevelUnit, governorate]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: topLevelUnit Context triple: [Imperial Russian administrative system, topLevelUnit, governorate]
-
A.
topLevelOf
Indicates that one entity is the highest or most overarching level within the structure or hierarchy of another entity.
-
B.
hasTopLevel
Indicates that one entity is the highest or primary element within a hierarchy or structure relative to another entity.
-
C.
unit
Indicates that two quantities are measured using the same standard unit of measurement.
-
D.
coreUnitType
Indicates that one entity is classified as the primary or fundamental type/category to which another entity (a core unit) belongs.
-
E.
topDivisionOf
chosen
Indicates that one administrative or organizational unit is the highest-level division within the structure of another entity.
- 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_69ad8b1793888190a5f70e4b21dc05a1 |
completed | March 8, 2026, 2:43 p.m. |
| NER | Named-entity recognition | batch_69adc580b08481908391283778d5ce14 |
completed | March 8, 2026, 6:52 p.m. |
| PD | Predicate disambiguation | batch_69adc041a8608190a2d543dab6d2ef6c |
completed | March 8, 2026, 6:30 p.m. |
Created at: March 8, 2026, 3:33 p.m.