Triple
T8016346
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | North Field |
E186626
|
entity |
| Predicate | hasRunway |
P105
|
FINISHED |
| Object |
Runway A
Runway A is a designated aircraft landing and takeoff strip located within North Field airport.
|
E707588
|
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: Runway A | Statement: [North Field, hasRunway, Runway A]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Runway A Context triple: [North Field, hasRunway, Runway A]
-
A.
Runway 4
Runway 4 is one end of a bidirectional airport runway, typically aligned toward a magnetic heading of approximately 040 degrees.
-
B.
Runway 5
Runway 5 is an airport runway designation indicating an approximate magnetic heading of 50 degrees, typically used when runway numbers are updated to reflect shifts in Earth’s magnetic variation.
-
C.
Runway 3R/21L
Runway 3R/21L is a primary paved runway at Tri-Cities Airport used for aircraft takeoffs and landings aligned roughly northeast–southwest.
-
D.
Runway 9R/27L
Runway 9R/27L is a primary paved runway at Orlando Sanford International Airport used for commercial and general aviation operations.
-
E.
Runway 3
Runway 3 is an airport runway designation indicating a magnetic heading of approximately 030 degrees, used to guide aircraft during takeoff and landing.
- 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: Runway A Triple: [North Field, hasRunway, Runway A]
Generated description
Runway A is a designated aircraft landing and takeoff strip located within North Field airport.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Runway A Target entity description: Runway A is a designated aircraft landing and takeoff strip located within North Field airport.
-
A.
Runway 4
Runway 4 is one end of a bidirectional airport runway, typically aligned toward a magnetic heading of approximately 040 degrees.
-
B.
Runway 5
Runway 5 is an airport runway designation indicating an approximate magnetic heading of 50 degrees, typically used when runway numbers are updated to reflect shifts in Earth’s magnetic variation.
-
C.
Runway 3R/21L
Runway 3R/21L is a primary paved runway at Tri-Cities Airport used for aircraft takeoffs and landings aligned roughly northeast–southwest.
-
D.
Runway 9R/27L
Runway 9R/27L is a primary paved runway at Orlando Sanford International Airport used for commercial and general aviation operations.
-
E.
Runway 3
Runway 3 is an airport runway designation indicating a magnetic heading of approximately 030 degrees, used to guide aircraft during takeoff and landing.
- 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_69ca82ac7fc081909b1398cf025423af |
completed | March 30, 2026, 2:03 p.m. |
| NER | Named-entity recognition | batch_69cb3df37a00819088780e5461bc5b41 |
completed | March 31, 2026, 3:22 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69cc56ba88b88190ad279d79d7f0ffd7 |
completed | March 31, 2026, 11:20 p.m. |
| NEDg | Description generation | batch_69cc58a9e94081908980e2c60be38642 |
completed | March 31, 2026, 11:28 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69cc5cbaefb481909eb325f0d27675c0 |
completed | March 31, 2026, 11:46 p.m. |
Created at: March 30, 2026, 5:20 p.m.