Triple
T18840472
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Great Lake River |
E460778
|
entity |
| Predicate | normalFlowDirection |
P113696
|
FINISHED |
| Object | from Tonlé Sap Lake to Mekong River |
—
|
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: from Tonlé Sap Lake to Mekong River | Statement: [Great Lake River, normalFlowDirection, from Tonlé Sap Lake to Mekong River]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: normalFlowDirection Context triple: [Great Lake River, normalFlowDirection, from Tonlé Sap Lake to Mekong River]
-
A.
hasDirectionOfFlow
chosen
Indicates that something moves or is transmitted from one entity or location toward another along a specific path or orientation.
-
B.
dataFlowDirection
Indicates the direction in which data moves or is transmitted from a source entity to a target entity.
-
C.
nonConductingDirection
Indicates a directional relationship along which conduction (such as electrical or thermal flow) does not occur or is blocked between entities.
-
D.
flowsNorthwardsTo
Indicates that something moves or is directed in a generally northward direction until it reaches or connects with another specified entity.
-
E.
feedDirection
Indicates the direction or orientation in which material, energy, or information is supplied or fed from one entity to another.
- 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_69d8dcfa11e4819090ab1ef5bdcd2b2e |
completed | April 10, 2026, 11:20 a.m. |
| NER | Named-entity recognition | batch_69e5b8e8f57081909edbbcaf56189816 |
completed | April 20, 2026, 5:26 a.m. |
| PD | Predicate disambiguation | batch_69e48d1e7dac81909ea1e758c87773c5 |
completed | April 19, 2026, 8:06 a.m. |
Created at: April 10, 2026, 11:56 a.m.