Triple
T2764475
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | LaGuardia Airport |
E61301
|
entity |
| Predicate | hasRunway |
P105
|
FINISHED |
| Object | Runway 13/31 |
E61749
|
NE 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: Runway 13/31 | Statement: [LaGuardia Airport, hasRunway, Runway 13/31]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Runway 13/31 Context triple: [LaGuardia Airport, hasRunway, Runway 13/31]
-
A.
Runway 13/31
chosen
Runway 13/31 is one of the primary intersecting runways at New York’s LaGuardia Airport, used for both arrivals and departures in varying wind and traffic conditions.
-
B.
Runway 13/31
Runway 13/31 is a primary paved runway at Yao Airport in Japan, used for takeoffs and landings by the airport’s aircraft.
-
C.
Runway 13/31
Runway 13/31 is a primary paved runway at LaGrange–Callaway Airport in Georgia, used for general aviation takeoffs and landings.
-
D.
Runway 13/31
Runway 13/31 is a primary military airfield runway at Cannon Air Force Base in New Mexico, used for takeoffs and landings by U.S. Air Force aircraft.
-
E.
Runway 13/31
Runway 13/31 is one of the primary paved runways at Vancouver International Airport, used for handling a mix of domestic and international air traffic under varying wind and weather conditions.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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_69ab4b7bab6c8190a5c2efef19a8ef34 |
completed | March 6, 2026, 9:47 p.m. |
| NER | Named-entity recognition | batch_69abdd541c2c8190a983a6f6a0b24ed9 |
completed | March 7, 2026, 8:09 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b5335421348190a18cb74cdd885c82 |
completed | March 14, 2026, 10:07 a.m. |
Created at: March 6, 2026, 9:57 p.m.