Triple
T18840473
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Great Lake River |
E460778
|
entity |
| Predicate | reversedFlowDirection |
P9300
|
FINISHED |
| Object | from Mekong River to Tonlé Sap Lake |
—
|
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 Mekong River to Tonlé Sap Lake | Statement: [Great Lake River, reversedFlowDirection, from Mekong River to Tonlé Sap Lake]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: reversedFlowDirection Context triple: [Great Lake River, reversedFlowDirection, from Mekong River to Tonlé Sap Lake]
-
A.
hasDirectionOfFlow
Indicates that something moves or is transmitted from one entity or location toward another along a specific path or orientation.
-
B.
reversed
chosen
Indicates that the direction or order of a previously defined relationship or sequence between entities is inverted.
-
C.
dataFlowDirection
Indicates the direction in which data moves or is transmitted from a source entity to a target entity.
-
D.
reversedTrendOf
Indicates that one trend is the inverse or opposite-direction counterpart of another trend, such that when one increases or moves in a certain direction, the other correspondingly decreases or moves in the opposite direction.
-
E.
reverseFeature
Indicates that one feature is the inverse or opposite counterpart of another feature in a given context.
- 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.