Triple
T4638773
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Upper Chinook |
E101598
|
entity |
| Predicate | relativePositionToLowerChinook |
P23578
|
FINISHED |
| Object | upstream |
—
|
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: upstream | Statement: [Upper Chinook, relativePositionToLowerChinook, upstream]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: relativePositionToLowerChinook Context triple: [Upper Chinook, relativePositionToLowerChinook, upstream]
-
A.
typicalPilotPosition
Indicates the usual or standard spatial position or placement where a pilot is located relative to the associated object or system.
-
B.
relativePosition
chosen
Indicates the spatial relationship of one entity’s location with respect to another entity’s position.
-
C.
lowerDeckDirection
Indicates the direction or orientation associated with movement or positioning on the lower deck of a structure or vehicle.
-
D.
liesBelow
Indicates that one entity is positioned at a lower vertical level than another entity.
-
E.
lowerLocation
Indicates that one entity is located physically below or at a lower vertical position relative to 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_69bd43d3bc7c81908f81fcf380476b0f |
completed | March 20, 2026, 12:55 p.m. |
| NER | Named-entity recognition | batch_69bd5a8e0ee88190becab97d2ef1571a |
completed | March 20, 2026, 2:32 p.m. |
| PD | Predicate disambiguation | batch_69bd5233cb5081908807e2b150f0ca06 |
completed | March 20, 2026, 1:57 p.m. |
Created at: March 20, 2026, 1:13 p.m.