Triple
T37130561
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sentosa Golf Club |
E919503
|
entity |
| Predicate | formerCourseName |
P202836
|
FINISHED |
| Object | Tanjong 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: Tanjong Course | Statement: [Sentosa Golf Club, formerCourseName, Tanjong Course]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: formerCourseName Context triple: [Sentosa Golf Club, formerCourseName, Tanjong Course]
-
A.
formerCourse
Indicates that one entity previously served as a course for another entity but no longer holds that status.
-
B.
formerCourseUsedFor
Indicates that one course previously served as preparation, credit, or a prerequisite fulfilling the role now associated with another course.
-
C.
previousCourse
Indicates that one course must be taken before another, typically as a prerequisite or earlier offering in a sequence.
-
D.
courseName
Indicates the specific name or title assigned to a course in an educational context.
-
E.
formerUniversityName
Indicates that an institution previously had a different official university name than the one it currently holds.
- F. None of above. chosen
Provenance (4 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_69f76e9d13e48190a108f7fbf80ff375 |
completed | May 3, 2026, 3:49 p.m. |
| NER | Named-entity recognition | batch_6a00c3362dcc819096e49b882709fddd |
completed | May 10, 2026, 5:41 p.m. |
| PD | Predicate disambiguation | batch_6a00c2e5cdd88190a5f2d0f6a843cd56 |
completed | May 10, 2026, 5:39 p.m. |
| PDg | Predicate description generation | batch_6a00c3355498819088253d5e5c17267f |
completed | May 10, 2026, 5:41 p.m. |
Created at: May 3, 2026, 4:15 p.m.