Triple
T20224806
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | KPKB |
E495349
|
entity |
| Predicate | servesCity |
P82
|
FINISHED |
| Object | Parkersburg |
—
|
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: Parkersburg | Statement: [KPKB, servesCity, Parkersburg]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Parkersburg Context triple: [KPKB, servesCity, Parkersburg]
-
A.
Parkersburg, West Virginia
chosen
Parkersburg, West Virginia is a mid-sized city along the Ohio River that serves as a regional economic and transportation hub in western West Virginia.
-
B.
Petersburg, West Virginia
Petersburg, West Virginia, is a small city in the Potomac Highlands region known as a local commercial hub and gateway to nearby outdoor recreation areas such as Dolly Sods and Seneca Rocks.
-
C.
Clarksburg
Clarksburg is a small town located in the northern part of Massachusetts, near the Vermont border, known for its rural character and natural scenery.
-
D.
Morganstown
Morganstown is a village in Cardiff, Wales, situated near Radyr and forming part of the city's northern suburban area.
-
E.
Waynesborough
Waynesborough is the historic Pennsylvania estate that served as the ancestral home of the prominent Wayne family, including Revolutionary War General Anthony Wayne.
- 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_69da626cff80819097b530718a7c98b6 |
completed | April 11, 2026, 3:02 p.m. |
| NER | Named-entity recognition | batch_69e66fd8f1948190adbb947a7870bb43 |
completed | April 20, 2026, 6:26 p.m. |
Created at: April 11, 2026, 11:39 p.m.