Triple
T12354550
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Στρυμόνας |
E294576
|
entity |
| Predicate | χρησιμοποιείταιΓια |
P98
|
FINISHED |
| Object | άρδευση |
—
|
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: άρδευση | Statement: [Στρυμόνας, χρησιμοποιείταιΓια, άρδευση]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: χρησιμοποιείταιΓια Context triple: [Στρυμόνας, χρησιμοποιείταιΓια, άρδευση]
-
A.
usedFor
chosen
Indicates that one entity serves a purpose, function, or role in accomplishing, enabling, or supporting another entity or activity.
-
B.
isBelievedToBeUsedFor
Indicates that something is thought or assumed to serve a particular purpose or function, without certainty.
-
C.
usedForService
Indicates that one entity is employed, utilized, or designated to perform, support, or provide a particular service for another entity.
-
D.
denUse
Indicates that an entity uses or makes use of a particular den (or designated shelter/space) for its activities or habitation.
-
E.
usedWith
Indicates that one entity is typically or appropriately employed together with another entity in a combined or complementary 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_69d6ab6ccbec8190b09e2d357aa80064 |
completed | April 8, 2026, 7:24 p.m. |
| NER | Named-entity recognition | batch_69d93f8bc60c8190b0ceb84093e70db4 |
completed | April 10, 2026, 6:20 p.m. |
| PD | Predicate disambiguation | batch_69d93ecb5efc819086a3530282278bb1 |
completed | April 10, 2026, 6:17 p.m. |
Created at: April 8, 2026, 9:54 p.m.