Triple
T3630551
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Machame Route |
E76943
|
entity |
| Predicate | approachSide |
P30202
|
FINISHED |
| Object | southwestern slope of Mount Kilimanjaro |
—
|
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: southwestern slope of Mount Kilimanjaro | Statement: [Machame Route, approachSide, southwestern slope of Mount Kilimanjaro]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: approachSide Context triple: [Machame Route, approachSide, southwestern slope of Mount Kilimanjaro]
-
A.
hasApproachSide
chosen
Indicates that one entity has a particular side or direction from which another entity can approach or access it.
-
B.
approachDirection
Indicates the direction or bearing from which one entity moves closer to or advances toward another entity.
-
C.
approachRoute
Indicates the path or method taken by one entity as it moves toward or comes closer to another entity or target.
-
D.
approachLocation
Indicates that an entity moves closer to or heads toward a specified location.
-
E.
approachControl
Indicates that one entity moves closer to another entity in a deliberate or controlled manner.
- 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_69ad85dc03948190b35b7189e4175bcc |
completed | March 8, 2026, 2:21 p.m. |
| NER | Named-entity recognition | batch_69adc30136e88190922bb542971b5239 |
completed | March 8, 2026, 6:42 p.m. |
| PD | Predicate disambiguation | batch_69adb8410a5881909c94818d7060b2b0 |
completed | March 8, 2026, 5:56 p.m. |
Created at: March 8, 2026, 3:23 p.m.