Triple
T20310996
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Pikeville Cut-Through |
E510240
|
entity |
| Predicate | cutThrough |
P56986
|
FINISHED |
| Object | Peach Orchard Mountain |
—
|
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: Peach Orchard Mountain | Statement: [Pikeville Cut-Through, cutThrough, Peach Orchard Mountain]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: cutThrough Context triple: [Pikeville Cut-Through, cutThrough, Peach Orchard Mountain]
-
A.
cutOff
Indicates that one entity causes another entity to be disconnected, interrupted, or severed from a source, flow, or continuation.
-
B.
crossCut
chosen
Indicates that one entity intersects or passes through another, typically cutting across it from one side to the other.
-
C.
cutBy
Indicates that one entity is divided, severed, or shaped as a result of another entity performing a cutting action on it.
-
D.
cutDown
Indicates that an agent causes something standing or elevated (such as a tree or structure) to fall or be reduced by cutting.
-
E.
passesUnder
Indicates that one entity moves or extends beneath another entity, typically crossing below it without direct contact.
- 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_69e0b4c7491c8190961113c4283b10b0 |
completed | April 16, 2026, 10:07 a.m. |
| NER | Named-entity recognition | batch_69e677441f9c8190acf98dc92c77732b |
completed | April 20, 2026, 6:58 p.m. |
| PD | Predicate disambiguation | batch_69e55b21b09081909e46691b6f45a07f |
completed | April 19, 2026, 10:45 p.m. |
Created at: April 16, 2026, 11:19 a.m.