Triple
T30398491
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sunningdale Golf Club |
E773284
|
entity |
| Predicate | OldCoursePar |
P113132
|
FINISHED |
| Object | 70 |
—
|
LITERAL FINISHED |
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: 70 | Statement: [Sunningdale Golf Club, OldCoursePar, 70]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: OldCoursePar Context triple: [Sunningdale Golf Club, OldCoursePar, 70]
-
A.
golfCoursePar
chosen
Indicates the standard number of strokes a skilled golfer is expected to take to complete a particular golf course or hole.
-
B.
typicalCoursePar
Indicates that one course is a typical or standard parallel (i.e., alternative but equivalent) course to another within a curriculum or program.
-
C.
8thHolePar
Indicates that the par (expected number of strokes) is specified for the 8th hole of a golf course.
-
D.
typicalWinningScoreRelativeToPar
Indicates the usual or expected winning score in relation to the course’s par (e.g., how many strokes under or over par typically wins).
-
E.
16thHolePar
Indicates that the par (expected number of strokes) is being specified for the 16th hole of a 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_69f2248facd48190b183c3f3ca6daef7 |
completed | April 29, 2026, 3:32 p.m. |
| NER | Named-entity recognition | batch_69f686150f908190ba57742775f07870 |
completed | May 2, 2026, 11:17 p.m. |
| PD | Predicate disambiguation | batch_69f678d019fc8190913662cd2f87b857 |
completed | May 2, 2026, 10:21 p.m. |
Created at: April 29, 2026, 8:03 p.m.