Triple
T23058210
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Zemunik Donji |
E574219
|
entity |
| Predicate | airBaseFunction |
P144235
|
FINISHED |
| Object | pilot training |
—
|
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: pilot training | Statement: [Zemunik Donji, airBaseFunction, pilot training]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: airBaseFunction Context triple: [Zemunik Donji, airBaseFunction, pilot training]
-
A.
airService
Indicates that an air transportation service (such as flights or air routes) is provided or operates between the related entities.
-
B.
hasAirBaseFunction
chosen
Indicates that something serves the role or performs the functions of an air base, such as supporting aircraft operations, maintenance, or related activities.
-
C.
airCommander
Indicates that an entity serves as the commanding officer or leader of air forces or air operations for another entity.
-
D.
isAirBase
Indicates that the subject entity functions as a military air base, i.e., a facility used for operating, housing, and supporting aircraft and related activities.
-
E.
usesAirbase
Indicates that one entity operates from, accesses, or conducts activities at a particular airbase.
- 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_69e245ba7ae48190be606dbc54120e39 |
completed | April 17, 2026, 2:37 p.m. |
| NER | Named-entity recognition | batch_69f18681bec48190a8226b3d89d19b9f |
completed | April 29, 2026, 4:18 a.m. |
| PD | Predicate disambiguation | batch_69ef89d5f71881908b9f9d0c8aab278c |
completed | April 27, 2026, 4:07 p.m. |
Created at: April 17, 2026, 3:55 p.m.