Triple
T1788863
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Awash River Basin |
E39449
|
entity |
| Predicate | collectsRunoffFrom |
P4497
|
FINISHED |
| Object | central Ethiopian Highlands |
—
|
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: central Ethiopian Highlands | Statement: [Awash River Basin, collectsRunoffFrom, central Ethiopian Highlands]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: collectsRunoffFrom Context triple: [Awash River Basin, collectsRunoffFrom, central Ethiopian Highlands]
-
A.
runoffHeld
Indicates that a subsequent runoff election was conducted to determine a winner after an initial voting round did not produce a decisive result.
-
B.
drainsInto
chosen
Indicates that one entity serves as a source or conduit whose contents or flow are directed into another entity.
-
C.
drainageType
Indicates the kind or classification of drainage associated with or applied to an entity (e.g., how water is removed or flows from it).
-
D.
managesWaterFrom
Indicates that one entity is responsible for controlling, directing, or handling water originating from another entity.
-
E.
flowsIntoBodyOfWaterType
Indicates that one body of water moves or drains into another body of water of a specified type (e.g., river, lake, ocean).
- 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_69a88631854081909723959921e45c2b |
completed | March 4, 2026, 7:21 p.m. |
| NER | Named-entity recognition | batch_69ab75457e54819096b8c6ae8c65550c |
completed | March 7, 2026, 12:45 a.m. |
| PD | Predicate disambiguation | batch_69aa61d165688190924962a98e07ff69 |
completed | March 6, 2026, 5:10 a.m. |
Created at: March 4, 2026, 7:32 p.m.