Triple
T17103036
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Perth Airport |
E415025
|
entity |
| Predicate | hasRunway |
P105
|
FINISHED |
| Object |
Runway 06/24
Runway 06/24 is a principal paved runway at Perth Airport in Western Australia, used for handling a significant share of the airport’s commercial air traffic.
|
E1259132
|
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 06/24 | Statement: [Perth Airport, hasRunway, Runway 06/24]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Runway 06/24 Context triple: [Perth Airport, hasRunway, Runway 06/24]
-
A.
Runway 06/24
Runway 06/24 is one of the primary paved runways used for aircraft takeoffs and landings at Paris Orly Airport in France.
-
B.
Runway 06/24
Runway 06/24 is a principal runway at Istanbul’s Sabiha Gökçen International Airport, used for handling both domestic and international air traffic.
-
C.
Runway 06/24
Runway 06/24 is a primary paved runway at Lanseria International Airport in South Africa, aligned roughly northeast–southwest to accommodate prevailing winds and commercial traffic.
-
D.
Runway 06/24
Runway 06/24 is the primary paved runway at Lappeenranta Airport in Finland, used for both domestic and international air traffic operations.
-
E.
Runway 06/24
Runway 06/24 is a primary paved runway at Volgograd International Airport in Russia, used for handling the airport’s commercial air traffic.
- 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 06/24 Triple: [Perth Airport, hasRunway, Runway 06/24]
Generated description
Runway 06/24 is a principal paved runway at Perth Airport in Western Australia, used for handling a significant share of the airport’s commercial air traffic.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Runway 06/24 Target entity description: Runway 06/24 is a principal paved runway at Perth Airport in Western Australia, used for handling a significant share of the airport’s commercial air traffic.
-
A.
Runway 06/24
Runway 06/24 is a principal paved runway at Edinburgh Airport used for most commercial flight operations.
-
B.
Runway 06/24
Runway 06/24 is a principal paved runway at Shannon Airport in Ireland, used for handling commercial and other aircraft operations.
-
C.
Runway 06/24
Runway 06/24 is a primary paved runway at San Bernardino International Airport in California, used for aircraft takeoffs and landings aligned roughly northeast–southwest.
-
D.
Runway 06/24
Runway 06/24 is a primary paved runway at Volgograd International Airport in Russia, used for handling the airport’s commercial air traffic.
-
E.
Runway 06/24
Runway 06/24 is one of the primary paved runways used for aircraft takeoffs and landings at Paris Orly Airport in France.
- 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_69d886cfc8e88190b05ba466edd35591 |
completed | April 10, 2026, 5:12 a.m. |
| NER | Named-entity recognition | batch_69e3dc2495c88190b5b16a006a994faf |
completed | April 18, 2026, 7:31 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a0170e153808190b2a253f64da87737 |
completed | May 11, 2026, 6:02 a.m. |
| NEDg | Description generation | batch_6a01726ae14081909d11434e378d3e1c |
completed | May 11, 2026, 6:08 a.m. |
| NED2 | Entity disambiguation (via description) | batch_6a017525d8108190b2fff7d96beff345 |
completed | May 11, 2026, 6:20 a.m. |
Created at: April 10, 2026, 5:35 a.m.