Triple
T29584155
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Bakool region |
E753674
|
entity |
| Predicate | dominantLivelihoodSystem |
P162656
|
FINISHED |
| Object | rain-fed farming |
—
|
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: rain-fed farming | Statement: [Bakool region, dominantLivelihoodSystem, rain-fed farming]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: dominantLivelihoodSystem Context triple: [Bakool region, dominantLivelihoodSystem, rain-fed farming]
-
A.
livelihoodArea
chosen
Indicates the area or domain in which an entity earns its living or sustains its means of support.
-
B.
agriculturalDependence
Indicates that one entity relies on another for agricultural resources, production, or support.
-
C.
primaryLandUse
Indicates the main or dominant way in which a given piece of land is utilized or designated (e.g., residential, agricultural, commercial).
-
D.
agricultureShareOfGDP
Indicates the proportion of a country’s total economic output (GDP) that is generated by agricultural activities.
-
E.
majorLandUse
Indicates the primary way a given area of land is utilized or designated (e.g., residential, commercial, agricultural).
- 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_69f0ef80bf8c8190ad286e99f7df0c63 |
completed | April 28, 2026, 5:33 p.m. |
| NER | Named-entity recognition | batch_69f71996e1a48190ac59a1d66d7c44e8 |
completed | May 3, 2026, 9:47 a.m. |
| PD | Predicate disambiguation | batch_69f71820c6c88190ab38b4fa626d22cc |
completed | May 3, 2026, 9:40 a.m. |
Created at: April 28, 2026, 6:09 p.m.