Triple
T32388918
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Bishop Pass Trail |
E827612
|
entity |
| Predicate | trailheadAccessRoad |
P174017
|
FINISHED |
| Object | South Lake Road |
—
|
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: South Lake Road | Statement: [Bishop Pass Trail, trailheadAccessRoad, South Lake Road]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: trailheadAccessRoad Context triple: [Bishop Pass Trail, trailheadAccessRoad, South Lake Road]
-
A.
trailAccess
Indicates that one entity provides permission or a route for another entity to enter, use, or traverse a specific trail or pathway.
-
B.
trailheadIn
Indicates that a trailhead is located within or at a specific place or area.
-
C.
trailName
Indicates the name assigned to a specific trail or path in the relationship.
-
D.
roadTraverses
Indicates that a road passes through, crosses, or extends across a specified geographic area or feature.
-
E.
roadAccessVia
Indicates that one location or area is reachable from another specifically by using a particular road or road segment.
- 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_69f349184e7481909c6c54428cb9cf12 |
completed | April 30, 2026, 12:20 p.m. |
| NER | Named-entity recognition | batch_69f6c1d3dea88190985d0faef0c85551 |
completed | May 3, 2026, 3:32 a.m. |
| PD | Predicate disambiguation | batch_69f6ba6eb32c8190bf405b2011fa48f7 |
completed | May 3, 2026, 3:01 a.m. |
| PDg | Predicate description generation | batch_69f6bb344bb48190a8089f29c0063ded |
completed | May 3, 2026, 3:04 a.m. |
Created at: May 1, 2026, 12:52 a.m.