Triple
T24197915
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sultana |
E599883
|
entity |
| Predicate | rankingByElevationInAlaskaRange |
P39147
|
FINISHED |
| Object | second highest peak |
—
|
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: second highest peak | Statement: [Sultana, rankingByElevationInAlaskaRange, second highest peak]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: rankingByElevationInAlaskaRange Context triple: [Sultana, rankingByElevationInAlaskaRange, second highest peak]
-
A.
topographicProminenceRankInAlaska
Indicates the ranking position of a feature based on its topographic prominence relative to all other features in Alaska.
-
B.
rankBySizeInAlaska
Indicates that entities are ordered according to their relative size specifically within the geographic scope of Alaska.
-
C.
summitElevationRank
chosen
Indicates the relative position of a summit in an ordered list based on its elevation compared to other summits.
-
D.
rankInNorthAmericaByElevation
Indicates the relative position of a place in an ordered list of locations in North America based on their elevation.
-
E.
rankInAlaskaByLength
Indicates the position of something in an ordered list of items in Alaska when sorted by their length.
- 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_69e288ceaab88190899d0acb5931591d |
completed | April 17, 2026, 7:23 p.m. |
| NER | Named-entity recognition | batch_69f27c9ddfcc819096697a844b300cce |
completed | April 29, 2026, 9:48 p.m. |
| PD | Predicate disambiguation | batch_69f1c43e55688190b55fc20274ed471c |
completed | April 29, 2026, 8:41 a.m. |
Created at: April 17, 2026, 11:36 p.m.