Triple
T2399593
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Runway 15R/33L |
E47734
|
entity |
| Predicate | isParallelTo |
P1868
|
FINISHED |
| Object | Runway 15L/33R |
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 15L/33R | Statement: [Runway 15R/33L, isParallelTo, Runway 15L/33R]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Runway 15L/33R Context triple: [Runway 15R/33L, isParallelTo, Runway 15L/33R]
-
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 15R/33L
Runway 15R/33L is one of the primary parallel runways at Boston Logan International Airport, used for both arrivals and departures.
-
C.
Runway 13L/31R
Runway 13L/31R is one of the primary paved runways at Chicago Midway International Airport, used for both commercial and general aviation operations.
-
D.
Runway 13L/31R
Runway 13L/31R is one of the primary paved runways at Dallas Love Field Airport, used for commercial and general aviation takeoffs and landings.
-
E.
Runway 14L/32R
Runway 14L/32R is one of the primary paved runways at Moffett Field in California, used for military, research, and general aviation operations.
- 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_69a88a1c450c81909f61abb8b6863885 |
completed | March 4, 2026, 7:38 p.m. |
| NER | Named-entity recognition | batch_69abc8c95d8c819088e4bb4fb32452ae |
completed | March 7, 2026, 6:42 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b333f7b3848190bcef4a06a2b94dd1 |
completed | March 12, 2026, 9:45 p.m. |
Created at: March 4, 2026, 7:57 p.m.