Triple
T19068104
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ohrid St. Paul the Apostle Airport |
E466718
|
entity |
| Predicate | hasRunway |
P105
|
FINISHED |
| Object | Runway 01/19 |
—
|
NE NERFINISHED |
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: Runway 01/19 | Statement: [Ohrid St. Paul the Apostle Airport, hasRunway, Runway 01/19]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Runway 01/19 Context triple: [Ohrid St. Paul the Apostle Airport, hasRunway, Runway 01/19]
-
A.
Runway 01/19
chosen
Runway 01/19 is a primary paved runway at Niagara District Airport used for aircraft takeoffs and landings aligned roughly north–south.
-
B.
Runway 02/20
Runway 02/20 is the primary paved runway at Iki Airport in Nagasaki Prefecture, Japan, used for regional domestic flights.
-
C.
Runway 02/20
Runway 02/20 is a principal landing and takeoff strip at Carriel Sur International Airport in Chile, aligned roughly along the 020/200-degree magnetic headings.
-
D.
Runway 02/20
Runway 02/20 is one of the primary paved runways at Richmond International Airport, used for handling a range of commercial and general aviation traffic.
-
E.
Runway 02/20
Runway 02/20 is one of the principal landing and takeoff runways at Paris Orly Airport, serving both domestic and international air traffic.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69d8dd04f4488190b1121cc53ef2bfd6 |
completed | April 10, 2026, 11:20 a.m. |
| NER | Named-entity recognition | batch_69e5e19b94d08190865b62d98f718bb0 |
completed | April 20, 2026, 8:19 a.m. |
Created at: April 10, 2026, 12:03 p.m.