Triple
T14712825
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | PTL |
E345593
|
entity |
| Predicate | courseVariation |
P115479
|
FINISHED |
| Object | route changes significantly from year to year |
—
|
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: route changes significantly from year to year | Statement: [PTL, courseVariation, route changes significantly from year to year]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: courseVariation Context triple: [PTL, courseVariation, route changes significantly from year to year]
-
A.
courseCountVariability
Indicates how much the number of courses taken or offered varies across different times, groups, or conditions.
-
B.
coursePar
Indicates that two entities (such as paths, lines, or trajectories) run alongside each other in the same general direction without intersecting.
-
C.
courseType
Indicates the classification or category of a course based on its nature, level, or instructional format.
-
D.
courseIncludes
Indicates that a course contains or covers a particular component, such as a topic, module, lesson, or resource.
-
E.
courseShape
Indicates the geometric layout or configuration that defines the path or outline of a course.
- 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_69d822e4a8c08190a155df736bb7bc13 |
completed | April 9, 2026, 10:06 p.m. |
| NER | Named-entity recognition | batch_69deb982bf248190881e21a8a0861a3f |
completed | April 14, 2026, 10:02 p.m. |
| PD | Predicate disambiguation | batch_69de657c57ec8190ae0b9bb79a514566 |
completed | April 14, 2026, 4:04 p.m. |
| PDg | Predicate description generation | batch_69de716d3aac8190aaa6dc1f099b86e8 |
completed | April 14, 2026, 4:55 p.m. |
Created at: April 10, 2026, 1:29 a.m.