Triple
T36240932
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Long Thanh International Airport |
E891514
|
entity |
| Predicate | numberOfRunwaysPlanned |
P2956
|
FINISHED |
| Object | 4 |
—
|
LITERAL 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: 4 | Statement: [Long Thanh International Airport, numberOfRunwaysPlanned, 4]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: numberOfRunwaysPlanned Context triple: [Long Thanh International Airport, numberOfRunwaysPlanned, 4]
-
A.
numberOfRunways
chosen
Indicates the quantity of runways associated with a given entity, such as an airport or airfield.
-
B.
hasRunwayPlan
Indicates that an entity possesses or is associated with a planned configuration or strategy for a runway.
-
C.
runwayPlan
Indicates a planned or designated use of a runway for aircraft operations (such as takeoff, landing, or sequencing) within an airfield’s operational schedule.
-
D.
hasRunwaysAt
Indicates that a location or facility possesses one or more runways situated at that place.
-
E.
hasParallelRunway
Indicates that one runway is parallel in orientation and alignment to another runway.
- F. None of above.
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_69f76e44993481908fa75e4c48d0aab3 |
completed | May 3, 2026, 3:48 p.m. |
| NER | Named-entity recognition | batch_6a037c8d06cc8190ab6a5e18d9d2571e |
completed | May 12, 2026, 7:16 p.m. |
| PD | Predicate disambiguation | batch_6a037a0a54cc8190868c1bfa1590d1a6 |
completed | May 12, 2026, 7:05 p.m. |
Created at: May 3, 2026, 4:09 p.m.