Triple
T273614
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | KBWI |
E5198
|
entity |
| Predicate | hasRunway |
P105
|
FINISHED |
| Object | Runway 15R/33L |
E8391
|
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 15R/33L | Statement: [KBWI, hasRunway, Runway 15R/33L]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Runway 15R/33L Context triple: [KBWI, hasRunway, Runway 15R/33L]
-
A.
Runway 15L/33R
chosen
Runway 15L/33R is one of the primary paved runways at Baltimore/Washington International Thurgood Marshall Airport, used for handling commercial air traffic in both directions.
-
B.
Runway 10L/28R
Runway 10L/28R is one of the primary parallel runways at San Francisco International Airport, used extensively for both arrivals and departures.
-
C.
Runway 15/33
Runway 15/33 is one of the primary runways at Ronald Reagan Washington National Airport in Arlington, Virginia, serving commercial air traffic for the Washington, D.C. area.
-
D.
Runway 10/28
Runway 10/28 is a principal paved runway at José Martí International Airport in Havana, Cuba, used for handling a significant share of the airport’s commercial air traffic.
-
E.
Runway 05L/23R
Runway 05L/23R is one of the main parallel runways at Manchester Airport, used for handling a high volume of commercial air traffic.
- 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_69a257e6c8788190987dfe705ca2912a |
completed | Feb. 28, 2026, 2:50 a.m. |
| NER | Named-entity recognition | batch_69a25dd0a99c819089968a5400c58c5f |
completed | Feb. 28, 2026, 3:15 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69a38f537f1c8190a59ac4669498a3fc |
completed | March 1, 2026, 12:58 a.m. |
Created at: Feb. 28, 2026, 2:59 a.m.