Triple
T4304948
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Runway 10R/28L |
E99931
|
entity |
| Predicate | hasMagneticHeadingApproximate |
P54717
|
FINISHED |
| Object | 100 degrees |
—
|
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: 100 degrees | Statement: [Runway 10R/28L, hasMagneticHeadingApproximate, 100 degrees]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasMagneticHeadingApproximate Context triple: [Runway 10R/28L, hasMagneticHeadingApproximate, 100 degrees]
-
A.
hasMagneticHeading
chosen
Indicates the directional orientation of an entity relative to magnetic north, typically expressed as a magnetic compass bearing.
-
B.
hasReciprocalMagneticHeadingApprox
Indicates that two entities have magnetic headings that are approximately reciprocal (differing by about 180 degrees from each other).
-
C.
hasApproachHeading
Indicates that an entity follows or is aligned with a specified heading or direction when making an approach.
-
D.
hasMagneticMoment
Indicates that an entity possesses a magnetic moment, characterizing the strength and orientation of its magnetism.
-
E.
hasRelationToTrueHeading
Indicates that an entity has a specified relationship or correspondence to a true (reference) heading or direction.
- 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_69b345528ebc8190b5abc7e95094792d |
completed | March 12, 2026, 10:59 p.m. |
| NER | Named-entity recognition | batch_69b350b8e1cc819094ce3d6f6c8da767 |
completed | March 12, 2026, 11:48 p.m. |
| PD | Predicate disambiguation | batch_69b347ff45cc8190b0cc335a94cc3d73 |
completed | March 12, 2026, 11:10 p.m. |
Created at: March 12, 2026, 11:09 p.m.