Triple
T23993176
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | MIT course 2.007 |
E605119
|
entity |
| Predicate | predecessorCourse |
P97
|
FINISHED |
| Object | MIT course 2.70 |
—
|
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: MIT course 2.70 | Statement: [MIT course 2.007, predecessorCourse, MIT course 2.70]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: predecessorCourse Context triple: [MIT course 2.007, predecessorCourse, MIT course 2.70]
-
A.
previousCourse
Indicates that one course must be taken before another, typically as a prerequisite or earlier offering in a sequence.
-
B.
formerCourse
Indicates that one entity previously served as a course for another entity but no longer holds that status.
-
C.
formerCourseUsedFor
Indicates that one course previously served as preparation, credit, or a prerequisite fulfilling the role now associated with another course.
-
D.
predecessor
chosen
Indicates that one entity comes before another in an ordered sequence or succession.
-
E.
programPredecessor
Indicates that one program temporally or logically precedes another in a sequence or hierarchy of programs.
- 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_69e295463f7c8190b1c19dbd114641b9 |
completed | April 17, 2026, 8:17 p.m. |
| NER | Named-entity recognition | batch_69f1d38ce7fc8190a488991b6f61416b |
completed | April 29, 2026, 9:46 a.m. |
| PD | Predicate disambiguation | batch_69f1615994c48190a5de95d3f7e5cd0a |
completed | April 29, 2026, 1:39 a.m. |
Created at: April 17, 2026, 9:37 p.m.