Triple
T27450473
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Runway 23 |
E692423
|
entity |
| Predicate | isOrientedRelativeTo |
P29992
|
FINISHED |
| Object | local magnetic north |
—
|
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: local magnetic north | Statement: [Runway 23, isOrientedRelativeTo, local magnetic north]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: isOrientedRelativeTo Context triple: [Runway 23, isOrientedRelativeTo, local magnetic north]
-
A.
isRelativeTo
Indicates that one entity has a familial or kinship relationship to another entity.
-
B.
isInDirectionOf
chosen
Indicates that one entity is oriented or positioned toward the direction in which another entity lies.
-
C.
meetsInRelationTo
Indicates that two or more entities come together or interact within the context of a specified relationship or circumstance.
-
D.
positionedRelativeTo
Indicates that one entity’s spatial location is defined or described in relation to the position of another entity.
-
E.
angleRelation
Indicates a relationship specifying how two or more angles are related to each other, such as being equal, complementary, supplementary, or otherwise geometrically constrained.
- 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_69ef5206c9248190b5975c2a7f9d229c |
completed | April 27, 2026, 12:09 p.m. |
| NER | Named-entity recognition | batch_69f62dc5a7948190b74476634f251a0e |
completed | May 2, 2026, 5 p.m. |
| PD | Predicate disambiguation | batch_69f623aaf40081909f947431424a1d55 |
completed | May 2, 2026, 4:17 p.m. |
Created at: April 27, 2026, 12:47 p.m.