Triple
T19791635
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Eastern Mongolia |
E475424
|
entity |
| Predicate | hasTraditionalLivestock |
P47296
|
FINISHED |
| Object | sheep |
—
|
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: sheep | Statement: [Eastern Mongolia, hasTraditionalLivestock, sheep]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasTraditionalLivestock Context triple: [Eastern Mongolia, hasTraditionalLivestock, sheep]
-
A.
hasTraditionalAnimalBreed
Indicates that an entity is associated with or possesses an animal that belongs to a recognized traditional breed.
-
B.
primaryLivestock
Indicates that the specified livestock type is the main or most important kind of animal raised or kept by an entity.
-
C.
livestockUse
Indicates how an entity is used or managed in relation to livestock, such as for raising, feeding, housing, or supporting livestock activities.
-
D.
hasPastoralStructure
Indicates that an entity possesses or is organized according to a pastoral (shepherding or ministerial) governance or structural arrangement.
-
E.
typeOfLivestock
chosen
Indicates the specific kind or category of livestock associated with or involved in a given context or 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_69d8e51b014081908b263e167370529a |
completed | April 10, 2026, 11:55 a.m. |
| NER | Named-entity recognition | batch_69e653c37a3c819080f195d58adaaa7b |
completed | April 20, 2026, 4:26 p.m. |
| PD | Predicate disambiguation | batch_69e5305858108190bbbfdb9ba3ab9f80 |
completed | April 19, 2026, 7:43 p.m. |
Created at: April 10, 2026, 1:49 p.m.