Triple
T25102118
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sunken Meadow State Park |
E628755
|
entity |
| Predicate | hasGolfCourseName |
P4286
|
FINISHED |
| Object | Sunken Meadow State Park Golf Course |
—
|
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: Sunken Meadow State Park Golf Course | Statement: [Sunken Meadow State Park, hasGolfCourseName, Sunken Meadow State Park Golf Course]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasGolfCourseName Context triple: [Sunken Meadow State Park, hasGolfCourseName, Sunken Meadow State Park Golf Course]
-
A.
hasGolfCourse
chosen
Indicates that one entity possesses, contains, or includes a golf course as part of its facilities or attributes.
-
B.
hasGolfCourseCluster
Indicates that an entity is associated with or contains a group or concentration of golf courses in a particular area.
-
C.
golfCourseInstanceOf
Indicates that a particular golf course is an instance of a specified golf course type or class.
-
D.
hasGolfDestination
Indicates that one entity serves as a golf-related destination or location for another entity.
-
E.
golfCourseStyle
Indicates the design or architectural style that characterizes a particular golf course.
- 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_69e2ff3071548190b62d1ac237397197 |
completed | April 18, 2026, 3:49 a.m. |
| NER | Named-entity recognition | batch_69f464be45448190b42c7d880d8550c8 |
completed | May 1, 2026, 8:30 a.m. |
| PD | Predicate disambiguation | batch_69f44d8043b081908bbffd7f044b4f26 |
completed | May 1, 2026, 6:51 a.m. |
Created at: April 18, 2026, 6:26 a.m.