Triple
T8835011
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Blue Mesa |
E210244
|
entity |
| Predicate | Blue Mesa Trail_type |
P77360
|
FINISHED |
| Object | loop trail |
—
|
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: loop trail | Statement: [Blue Mesa, Blue Mesa Trail_type, loop trail]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: Blue Mesa Trail_type Context triple: [Blue Mesa, Blue Mesa Trail_type, loop trail]
-
A.
locatedOnEasternSlopeOf
Indicates that one entity is situated on the eastern slope or side of another geographic feature or elevation.
-
B.
isOnLewisAndClarkTrail
Indicates that a location lies along, or is officially recognized as part of, the Lewis and Clark National Historic Trail.
-
C.
isPartOfTrailSystem
chosen
Indicates that something belongs to, or is included within, a larger trail network or trail system.
-
D.
liesOnContinentalDivide
Indicates that one entity is located on the continental divide, the geographic boundary separating distinct drainage basins or watersheds.
-
E.
largestCliffDwelling
Indicates that the subject is the largest cliff dwelling (by size, capacity, or extent) among a relevant set of cliff dwellings.
- 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_69ca8388549c819095fd94eadefbb007 |
completed | March 30, 2026, 2:07 p.m. |
| NER | Named-entity recognition | batch_69cc60686cac8190b3138db40b6fe058 |
completed | April 1, 2026, 12:01 a.m. |
| PD | Predicate disambiguation | batch_69cc5c23d08481908d8c9b0ad3d1dc00 |
completed | March 31, 2026, 11:43 p.m. |
Created at: March 30, 2026, 6:47 p.m.