Triple
T2843164
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Boston Logan International Airport |
E62516
|
entity |
| Predicate | hasRunway |
P105
|
FINISHED |
| Object |
4L/22R
4L/22R is one of the primary runways at Boston Logan International Airport, used for both arrivals and departures in alignment with prevailing wind directions.
|
E303549
|
NE FINISHED |
How this triple was built (4 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: 4L/22R | Statement: [Boston Logan International Airport, hasRunway, 4L/22R]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: 4L/22R Context triple: [Boston Logan International Airport, hasRunway, 4L/22R]
-
A.
12R/30L
12R/30L is a primary paved runway at St. Louis Lambert International Airport used for aircraft takeoffs and landings.
-
B.
10L/28R
10L/28R is a primary east–west runway at Palm Beach International Airport used for both commercial and general aviation operations.
-
C.
L6L
L6L is a Canadian postal code prefix serving part of the town of Oakville in southern Ontario.
-
D.
LC4
LC4 is an iconic modernist chaise longue designed by Le Corbusier, Pierre Jeanneret, and Charlotte Perriand, renowned for its adjustable reclining form and tubular steel frame.
-
E.
10R/28L
10R/28L is a primary east–west runway at Fort Lauderdale–Hollywood International Airport used for commercial air traffic operations.
- F. None of above. chosen
- G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg
Description generation
gpt-5.1
Instruction
Generate a one-sentence description of the target entity. You are given a context triple in the form (subject, predicate, object), where the object is the target entity. # Instructions Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. Avoid repeating the information from the triple, unless really essential. # Response Format Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: 4L/22R Triple: [Boston Logan International Airport, hasRunway, 4L/22R]
Generated description
4L/22R is one of the primary runways at Boston Logan International Airport, used for both arrivals and departures in alignment with prevailing wind directions.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: 4L/22R Target entity description: 4L/22R is one of the primary runways at Boston Logan International Airport, used for both arrivals and departures in alignment with prevailing wind directions.
-
A.
12R/30L
12R/30L is a primary paved runway at St. Louis Lambert International Airport used for aircraft takeoffs and landings.
-
B.
10L/28R
10L/28R is a primary east–west runway at Palm Beach International Airport used for both commercial and general aviation operations.
-
C.
L6L
L6L is a Canadian postal code prefix serving part of the town of Oakville in southern Ontario.
-
D.
LC4
LC4 is an iconic modernist chaise longue designed by Le Corbusier, Pierre Jeanneret, and Charlotte Perriand, renowned for its adjustable reclining form and tubular steel frame.
-
E.
10R/28L
10R/28L is a primary east–west runway at Fort Lauderdale–Hollywood International Airport used for commercial air traffic operations.
- F. None of above. chosen
Provenance (5 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_69ab4c3d16bc81908b3a1c98fbd287fe |
completed | March 6, 2026, 9:50 p.m. |
| NER | Named-entity recognition | batch_69abdf1898748190b031a2bd2091c0c0 |
completed | March 7, 2026, 8:17 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69afe8d570388190b4ed81ace605c6c3 |
completed | March 10, 2026, 9:48 a.m. |
| NEDg | Description generation | batch_69afe9ba068881908727c82d5eddb974 |
completed | March 10, 2026, 9:51 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69b00412e7448190898050f18f64ea9a |
completed | March 10, 2026, 11:44 a.m. |
Created at: March 6, 2026, 10:01 p.m.