Triple
T19264567
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tivat Airport |
E481736
|
entity |
| Predicate | openedForCivilTraffic |
P84489
|
FINISHED |
| Object | 20th century |
—
|
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: 20th century | Statement: [Tivat Airport, openedForCivilTraffic, 20th century]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: openedForCivilTraffic Context triple: [Tivat Airport, openedForCivilTraffic, 20th century]
-
A.
openedToCivilianTraffic
chosen
Indicates that a previously restricted or closed route, facility, or infrastructure has been made accessible for use by civilian (non-military) traffic.
-
B.
openedForThroughTraffic
Indicates that a route or segment is available and accessible for vehicles to pass through (not just for local access), allowing continuous through traffic.
-
C.
openedToRoadTraffic
Indicates that something, such as a structure or route, has begun allowing regular use by vehicles or road users.
-
D.
reopenedToTraffic
Indicates that a previously closed route or transportation facility has been opened again for use by traffic.
-
E.
openedToPassengerTraffic
Indicates that a transportation facility or route began operating and accepting passengers for regular 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_69d8e8ce54cc8190998418ff1f66ef28 |
completed | April 10, 2026, 12:10 p.m. |
| NER | Named-entity recognition | batch_69e5fb8bce6881908395836960762672 |
completed | April 20, 2026, 10:10 a.m. |
| PD | Predicate disambiguation | batch_69e4dd07a7208190afcd51ba1dc87c33 |
completed | April 19, 2026, 1:47 p.m. |
Created at: April 10, 2026, 1:29 p.m.