Triple
T30663628
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | The Roller Coaster Capital of the World |
E780598
|
entity |
| Predicate | locationOfSubjectEntity |
P47308
|
FINISHED |
| Object | Sandusky, Ohio |
—
|
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: Sandusky, Ohio | Statement: [The Roller Coaster Capital of the World, locationOfSubjectEntity, Sandusky, Ohio]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: locationOfSubjectEntity Context triple: [The Roller Coaster Capital of the World, locationOfSubjectEntity, Sandusky, Ohio]
-
A.
subjectLocation
chosen
Indicates that one entity is located at, in, or near the place or position specified by another entity.
-
B.
objectLocation
Indicates that one entity is located at, in, or on another entity or spatial region.
-
C.
subjectLocationType
Indicates the type or category of location associated with the subject in the relationship.
-
D.
hasSubjectPlace
Indicates that something is associated with or occurs in a particular subject-related place or location.
-
E.
sourceLocatedOn
Indicates that the source entity is physically situated on the surface or area of the target entity.
- 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_69f224a6d10481909290be1a00fc83b3 |
completed | April 29, 2026, 3:32 p.m. |
| NER | Named-entity recognition | batch_6a00d24043e8819090cc473b6c0923d0 |
completed | May 10, 2026, 6:45 p.m. |
| PD | Predicate disambiguation | batch_6a00d1ec12fc81908c514ed088ef8300 |
completed | May 10, 2026, 6:43 p.m. |
Created at: April 29, 2026, 8:31 p.m.