Triple
T27830918
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Duncannon, Pennsylvania |
E703092
|
entity |
| Predicate | trailPassesThrough |
P54144
|
FINISHED |
| Object | Appalachian Trail |
E14101
|
NE 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: Appalachian Trail | Statement: [Duncannon, Pennsylvania, trailPassesThrough, Appalachian Trail]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: trailPassesThrough Context triple: [Duncannon, Pennsylvania, trailPassesThrough, Appalachian Trail]
-
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.
travelsThrough
chosen
Indicates that something moves along, passes across, or is routed via a particular path, medium, or location.
-
C.
isPassedThroughBy
Indicates that something serves as a medium, route, or channel through which another thing moves, flows, or is transmitted.
-
D.
roadTraverses
Indicates that a road passes through, crosses, or extends across a specified geographic area or feature.
-
E.
passesThroughPoint
Indicates that a path, line, or trajectory intersects or goes through a specific point in space.
- F. None of above.
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_69ef840b94b08190950a4f77296938b2 |
completed | April 27, 2026, 3:43 p.m. |
| NER | Named-entity recognition | batch_69f63b317e048190963989b732b25b91 |
completed | May 2, 2026, 5:58 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a12f72ebea88190a73e6a1086d00faf |
completed | May 24, 2026, 1:03 p.m. |
| PD | Predicate disambiguation | batch_69f6370ea79c81909b761821ee0fa698 |
completed | May 2, 2026, 5:40 p.m. |
Created at: April 27, 2026, 5:56 p.m.