Triple
T18392422
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Derbent |
E449765
|
entity |
| Predicate | agriculturalProductionType |
P114419
|
FINISHED |
| Object | crop 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: crop farming | Statement: [Derbent, agriculturalProductionType, crop farming]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: agriculturalProductionType Context triple: [Derbent, agriculturalProductionType, crop farming]
-
A.
agriculturalProduce
Indicates that one entity is an agricultural product (such as crops or livestock-derived goods) produced by or associated with another entity.
-
B.
hasAgriculturalProduction
Indicates that an entity engages in or is characterized by the production of agricultural goods such as crops or livestock.
-
C.
cultivationType
chosen
Indicates the method or system by which something (typically crops or land) is cultivated or farmed.
-
D.
agriculturalPractice
Indicates a relationship where an entity engages in, applies, or is associated with a specific method or technique of agriculture or farming.
-
E.
agricultureUse
Indicates that something is used for, involved in, or designated for agricultural activities or purposes.
- 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_69d8b9fab8a8819086a9ddc0871715e0 |
completed | April 10, 2026, 8:51 a.m. |
| NER | Named-entity recognition | batch_69e518435cf481908393c1eb2b4ba659 |
completed | April 19, 2026, 6 p.m. |
| PD | Predicate disambiguation | batch_69e44ff1f92c8190afbb8e85d12bf2a9 |
completed | April 19, 2026, 3:45 a.m. |
Created at: April 10, 2026, 10:46 a.m.