Triple
T27569886
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Solu |
E696002
|
entity |
| Predicate | KhumbuRelation |
P13913
|
FINISHED |
| Object | south of Khumbu |
—
|
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: south of Khumbu | Statement: [Solu, KhumbuRelation, south of Khumbu]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: KhumbuRelation Context triple: [Solu, KhumbuRelation, south of Khumbu]
-
A.
associatedWithMountainRange
Indicates a relationship where something is connected or related in some way to a specific mountain range.
-
B.
associatedWithMountain
Indicates a relationship in which something has a connection, link, or relevance to a mountain.
-
C.
relativeToMountEverest
chosen
Indicates a relationship that compares or situates something in reference to Mount Everest, such as in terms of location, height, scale, or significance.
-
D.
isSourceAndSummitOf
Indicates that an entity serves both as the originating point (source) and the highest point (summit) of another entity or feature.
-
E.
isNamedSummitOf
Indicates that one entity is the officially designated summit (highest or principal point) of another entity, such as a mountain or geographic feature.
- 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_69ef53891af88190a193c5e2a1dac9b1 |
completed | April 27, 2026, 12:16 p.m. |
| NER | Named-entity recognition | batch_69f62febae708190bc3b9e4dab8c7698 |
completed | May 2, 2026, 5:10 p.m. |
| PD | Predicate disambiguation | batch_69f62c1921008190a62675a31f66a875 |
completed | May 2, 2026, 4:53 p.m. |
Created at: April 27, 2026, 1:43 p.m.