Triple
T26838949
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Hong Kong Diploma of Secondary Education curriculum |
E675716
|
entity |
| Predicate | endGrade |
P7842
|
FINISHED |
| Object | Secondary 6 |
—
|
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: Secondary 6 | Statement: [Hong Kong Diploma of Secondary Education curriculum, endGrade, Secondary 6]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: endGrade Context triple: [Hong Kong Diploma of Secondary Education curriculum, endGrade, Secondary 6]
-
A.
gradeIn
Indicates that an entity has a particular grade or score within a specified course, assignment, or evaluation context.
-
B.
grades
Indicates that one entity evaluates and assigns a score or level of performance to another entity.
-
C.
gradeStatus
Indicates the current evaluation state or standing of an entity’s grade, such as whether it is pending, provisional, finalized, or otherwise classified in terms of completion or validity.
-
D.
gradeWithin
Indicates that one value’s grade or level falls within a specified range or interval relative to another.
-
E.
gradeNumber
chosen
Indicates the numerical grade or level assigned to an entity within an ordered grading or classification system.
- 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_69eee9b8d5e88190a07d3455c0fbb21f |
completed | April 27, 2026, 4:44 a.m. |
| NER | Named-entity recognition | batch_69f61b4475588190a4708261118fad78 |
completed | May 2, 2026, 3:41 p.m. |
| PD | Predicate disambiguation | batch_69f611ad2eb48190ac1ed0090f13f7a9 |
completed | May 2, 2026, 3:01 p.m. |
Created at: April 27, 2026, 5:06 a.m.