Triple
T3909
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | John F. Kennedy International Airport |
E74
|
entity |
| Predicate | hasRunway |
P105
|
FINISHED |
| Object | Runway 04L/22R |
—
|
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: Runway 04L/22R | Statement: [John F. Kennedy International Airport, hasRunway, Runway 04L/22R]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasRunway Context triple: [John F. Kennedy International Airport, hasRunway, Runway 04L/22R]
-
A.
hasMajorAirport
Indicates that a location possesses at least one significant airport that serves as a primary hub for air travel in that area.
-
B.
hasAthletics
Indicates that an entity participates in, is associated with, or offers athletics-related activities or programs.
-
C.
hasNotableFacility
chosen
Indicates that an entity possesses or hosts a facility that is of particular significance, prominence, or interest.
-
D.
hasRegion
Indicates that an entity includes, contains, or is associated with a specific geographic or administrative region as part of its scope or structure.
-
E.
drivesOn
Indicates that an entity uses or travels along a particular route, surface, or roadway as its path of movement.
- 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_69a238d6b47881909e68288aed2fd858 |
completed | Feb. 28, 2026, 12:37 a.m. |
| NER | Named-entity recognition | batch_69a23bcc8eb48190b897cc331563980a |
completed | Feb. 28, 2026, 12:50 a.m. |
| PD | Predicate disambiguation | batch_69a23994309081909ff3e869deef2156 |
completed | Feb. 28, 2026, 12:40 a.m. |
Created at: Feb. 28, 2026, 12:40 a.m.