Triple
T36008375
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ersari Turkmen |
E1041333
|
entity |
| Predicate | traditionalAnimalHerded |
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: [Ersari Turkmen, traditionalAnimalHerded, sheep]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: traditionalAnimalHerded Context triple: [Ersari Turkmen, traditionalAnimalHerded, sheep]
-
A.
primaryLivestock
Indicates that the specified livestock type is the main or most important kind of animal raised or kept by an entity.
-
B.
useOfLivestock
Indicates the action or practice of employing livestock for a particular purpose or function.
-
C.
hasTraditionalAnimalBreed
Indicates that an entity is associated with or possesses an animal that belongs to a recognized traditional breed.
-
D.
secondaryLivestock
Indicates that the referenced livestock are of secondary or lesser importance in relation to a primary group of livestock.
-
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_69f76e2a02208190aedd1f9025a8b300 |
completed | May 3, 2026, 3:47 p.m. |
| NER | Named-entity recognition | batch_69ff7bc112088190851501fb2a16103d |
completed | May 9, 2026, 6:24 p.m. |
| PD | Predicate disambiguation | batch_69ff7b45507c81909753866ad733601a |
completed | May 9, 2026, 6:21 p.m. |
Created at: May 3, 2026, 4:07 p.m.