Triple
T36644542
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 10L/28R |
E904670
|
entity |
| Predicate | hasDirectionLowEnd |
P30196
|
FINISHED |
| Object | approximately 100 degrees magnetic heading |
—
|
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: approximately 100 degrees magnetic heading | Statement: [10L/28R, hasDirectionLowEnd, approximately 100 degrees magnetic heading]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasDirectionLowEnd Context triple: [10L/28R, hasDirectionLowEnd, approximately 100 degrees magnetic heading]
-
A.
hasLowPowerVariant
Indicates that an entity has a related version or configuration designed to operate with reduced power consumption compared to the standard one.
-
B.
hasLow
Indicates that an entity possesses a value, level, or amount of something that is below a defined or expected threshold.
-
C.
hasDirectionType
chosen
Indicates that something possesses or is associated with a specific type or category of direction.
-
D.
hasLowSupportFor
Indicates that one entity provides insufficient or weak backing, endorsement, or assistance for another entity or proposition.
-
E.
hasDirectionVariant
Indicates that one entity is a directional variant or orientation-specific form of another entity.
- 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_69f76e6d3a3c81909db73eda9e0516bd |
completed | May 3, 2026, 3:49 p.m. |
| NER | Named-entity recognition | batch_69ff6a4ce9a08190b98abde3a170dd69 |
completed | May 9, 2026, 5:09 p.m. |
| PD | Predicate disambiguation | batch_69ff69c11634819089d1084bd2c11534 |
completed | May 9, 2026, 5:07 p.m. |
Created at: May 3, 2026, 4:11 p.m.