Triple
T14427967
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Cumania region in medieval Hungary |
E357742
|
entity |
| Predicate | typeOfFrontier |
P697
|
FINISHED |
| Object | march-like territory |
—
|
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: march-like territory | Statement: [Cumania region in medieval Hungary, typeOfFrontier, march-like territory]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: typeOfFrontier Context triple: [Cumania region in medieval Hungary, typeOfFrontier, march-like territory]
-
A.
typeOfFrontierUnit
Indicates that one unit is classified as a specific type or category of frontier unit in relation to another.
-
B.
frontSightType
Indicates the specific kind or design of the front sight used on an object, typically a firearm or similar aiming device.
-
C.
frontType
chosen
Indicates the type or category of a front (e.g., boundary or leading side) that one entity presents or forms relative to another.
-
D.
FrontierStatus
Indicates the status or condition of something in relation to a boundary, edge, or frontier context (such as being at, beyond, or within that frontier).
-
E.
typeOfFigure
Indicates that one entity is a specific kind or category of geometric figure relative to another.
- 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_69d8279402a88190821ffa39ae15bccf |
completed | April 9, 2026, 10:26 p.m. |
| NER | Named-entity recognition | batch_69de91154de881909266ae88d1545685 |
completed | April 14, 2026, 7:10 p.m. |
| PD | Predicate disambiguation | batch_69de5c30467881908e770e3940295641 |
completed | April 14, 2026, 3:24 p.m. |
Created at: April 10, 2026, 1:18 a.m.