Triple
T23907424
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sahune |
E601238
|
entity |
| Predicate | hasAgriculturalSpeciality |
P25683
|
FINISHED |
| Object | olive cultivation |
—
|
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: olive cultivation | Statement: [Sahune, hasAgriculturalSpeciality, olive cultivation]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasAgriculturalSpeciality Context triple: [Sahune, hasAgriculturalSpeciality, olive cultivation]
-
A.
hasAgriculturalType
Indicates that an entity is associated with or classified by a specific type or category of agriculture.
-
B.
hasAgriculturalCharacter
Indicates that something possesses qualities, features, or uses typical of agriculture or farming activities.
-
C.
hasAgriculturalProduction
chosen
Indicates that an entity engages in or is characterized by the production of agricultural goods such as crops or livestock.
-
D.
hasAgriculturalAssociation
Indicates that there exists a formal or recognized connection between an entity and an agricultural organization, group, or activity.
-
E.
isAgriculturalCity
Indicates that a city is primarily characterized by agriculture-based activities, economy, or land use.
- 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_69e295364a488190bcac702e9bb7f764 |
completed | April 17, 2026, 8:16 p.m. |
| NER | Named-entity recognition | batch_69f1ce91e6088190b85b534ab361f888 |
completed | April 29, 2026, 9:25 a.m. |
| PD | Predicate disambiguation | batch_69f1614e24b48190a1c8fb5b7c75ee0f |
completed | April 29, 2026, 1:39 a.m. |
Created at: April 17, 2026, 8:36 p.m.