Triple
T19845397
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Horseshoe Run, West Virginia |
E476847
|
entity |
| Predicate | hasName |
P744
|
FINISHED |
| Object | Horseshoe Run |
—
|
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: Horseshoe Run | Statement: [Horseshoe Run, West Virginia, hasName, Horseshoe Run]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Horseshoe Run Context triple: [Horseshoe Run, West Virginia, hasName, Horseshoe Run]
-
A.
Horseshoe Run
chosen
Horseshoe Run is a small stream in West Virginia that flows through rugged Appalachian terrain before joining the Cheat River.
-
B.
Cherokee Run
Cherokee Run was a champion American Thoroughbred racehorse and successful sire known for his speed and influence in modern bloodlines.
-
C.
Stony Run
Stony Run is a small urban stream in Baltimore, Maryland, that flows through parkland and residential neighborhoods before joining the Jones Falls.
-
D.
Marsh Run
Marsh Run is a small stream in the Antietam Creek watershed that serves as one of its left-bank tributaries in the Mid-Atlantic region of the United States.
-
E.
Bear Run
Bear Run is a stream in southwestern Pennsylvania best known as the natural setting for Frank Lloyd Wright’s iconic Fallingwater house.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69d8e51d39d081909bcfafeaaf3d2fcc |
completed | April 10, 2026, 11:55 a.m. |
| NER | Named-entity recognition | batch_69e658091c608190b4eb9bcedd88e147 |
completed | April 20, 2026, 4:44 p.m. |
Created at: April 10, 2026, 1:51 p.m.