Triple
T133445
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Labrador Current |
E2699
|
entity |
| Predicate | flowsDirection |
P967
|
FINISHED |
| Object | southward |
—
|
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: southward | Statement: [Labrador Current, flowsDirection, southward]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: flowsDirection Context triple: [Labrador Current, flowsDirection, southward]
-
A.
hasTrafficDirection
Indicates that there is a specified flow or orientation of traffic associated with an entity (such as a road, lane, or route).
-
B.
outflow
chosen
Indicates the movement or discharge of something from an origin or source to the outside or to another location.
-
C.
trafficDirection
Indicates the direction in which traffic is intended or allowed to move relative to a given reference point or segment.
-
D.
flowControl
Indicates a relationship where one entity regulates, directs, or manages the rate or sequence of another entity’s operations or movement.
-
E.
trafficType
Indicates the category or nature of traffic involved in a given interaction, flow, or connection (e.g., type of network, data, or transport traffic).
- 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_69a2520c0f3481908b0ed054a2fca8d0 |
completed | Feb. 28, 2026, 2:25 a.m. |
| NER | Named-entity recognition | batch_69a25788b2688190a45b39447f702551 |
completed | Feb. 28, 2026, 2:48 a.m. |
| PD | Predicate disambiguation | batch_69a25650251c81908a6ea6368cd61198 |
completed | Feb. 28, 2026, 2:43 a.m. |
Created at: Feb. 28, 2026, 2:30 a.m.