Triple
T37937919
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Senqu |
E946398
|
entity |
| Predicate | isUpperCourseOf |
P82189
|
FINISHED |
| Object | Orange River |
—
|
NE NERFINISHED |
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: Orange River | Statement: [Senqu, isUpperCourseOf, Orange River]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: isUpperCourseOf Context triple: [Senqu, isUpperCourseOf, Orange River]
-
A.
hasUpperCourseIn
Indicates that the upper (initial) part of a river or watercourse lies within or flows through a specified geographic area or region.
-
B.
isUpperCourseNameOf
Indicates that one course is the higher-level or more advanced version in a course sequence relative to another course.
-
C.
upperCourseOf
chosen
Indicates that one watercourse represents the upstream or higher-elevation segment of another watercourse within the same river system.
-
D.
hasUpperCourseName
Indicates that an entity (such as a course instance or section) is associated with the name of the higher-level or parent course of which it is a part.
-
E.
upperCourseName
Indicates that one course’s name is the uppercase version of another course’s name.
- 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_69f76ef531ac8190ae6d99e5786e76ec |
completed | May 3, 2026, 3:51 p.m. |
| NER | Named-entity recognition | batch_69fbc7b78f9481909f4f8fc2e3fdcde1 |
completed | May 6, 2026, 10:59 p.m. |
| PD | Predicate disambiguation | batch_69fbbd18c9908190928d274f8731dfa8 |
completed | May 6, 2026, 10:13 p.m. |
Created at: May 3, 2026, 4:20 p.m.