Triple
T28252832
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Jordan River–Great Salt Lake basin |
E712357
|
entity |
| Predicate | majorTerminalLake |
P193296
|
FINISHED |
| Object | Great Salt Lake |
—
|
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: Great Salt Lake | Statement: [Jordan River–Great Salt Lake basin, majorTerminalLake, Great Salt Lake]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: majorTerminalLake Context triple: [Jordan River–Great Salt Lake basin, majorTerminalLake, Great Salt Lake]
-
A.
maximumLake
Indicates that the subject entity is the lake with the greatest value (such as size, volume, or another specified measure) among a given set of lakes.
-
B.
mouthLake
Indicates the location where a river or stream flows into and forms part of a lake.
-
C.
nearestLargeLake
Indicates that one entity is the closest large lake in distance to the other entity.
-
D.
hasMajorLake
Indicates that a geographic region or area contains at least one significant lake within its boundaries.
-
E.
upstreamLake
Indicates that one lake is situated upstream of another lake within the same water flow or drainage system.
- F. None of above. chosen
Provenance (4 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_69efb5207eb08190827e4c34048030b1 |
completed | April 27, 2026, 7:12 p.m. |
| NER | Named-entity recognition | batch_69fd4129a8848190a5002150278ac689 |
completed | May 8, 2026, 1:49 a.m. |
| PD | Predicate disambiguation | batch_69fd3e0515ec8190937c7af71ebc3875 |
completed | May 8, 2026, 1:36 a.m. |
| PDg | Predicate description generation | batch_69fd4128ed908190837ec9936774a1cf |
completed | May 8, 2026, 1:49 a.m. |
Created at: April 27, 2026, 11:06 p.m.