Triple
T19761437
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Lost Kennywood |
E474638
|
entity |
| Predicate | hasAttraction |
P105
|
FINISHED |
| Object | Pitt Fall |
—
|
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: Pitt Fall | Statement: [Lost Kennywood, hasAttraction, Pitt Fall]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Pitt Fall Context triple: [Lost Kennywood, hasAttraction, Pitt Fall]
-
A.
Pitt Fall
chosen
Pitt Fall was a former drop tower thrill ride at Kennywood amusement park known for its rapid vertical free-fall experience.
-
B.
Penn State White Out
Penn State White Out is a famous Penn State football tradition in which fans dress in all white to create an intimidating, visually striking atmosphere for major home night games at Beaver Stadium.
-
C.
Pitt
Pitt is the surname of William Pitt the Elder, an influential 18th-century British statesman and prime minister known for his leadership during the Seven Years' War.
-
D.
Pitt
Pitt is the commonly used nickname for the University of Pittsburgh, a major public research university based in Pittsburgh, Pennsylvania.
-
E.
Pitt
Pitt was the given name of Prince Leleiohoku II, a 19th-century Hawaiian royal and composer.
- 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_69d8e51a43a08190956bc6df13c91a77 |
completed | April 10, 2026, 11:55 a.m. |
| NER | Named-entity recognition | batch_69e6532004d08190944234d35e74085b |
completed | April 20, 2026, 4:24 p.m. |
Created at: April 10, 2026, 1:48 p.m.