Triple
T13001276
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | CSI 2* |
E322174
|
entity |
| Predicate | courseDifficulty |
P2406
|
FINISHED |
| Object | challenging courses |
—
|
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: challenging courses | Statement: [CSI 2*, courseDifficulty, challenging courses]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: courseDifficulty Context triple: [CSI 2*, courseDifficulty, challenging courses]
-
A.
difficulty
chosen
Indicates the level of challenge, complexity, or effort required to perform an action, solve a problem, or achieve a particular outcome.
-
B.
difficultyClassRange
Indicates the range of difficulty classes within which an action, task, or challenge is considered to fall.
-
C.
difficultySource
Indicates that one entity is the cause, origin, or contributing factor to the difficulty or challenge experienced in relation to another entity or situation.
-
D.
difficultyRelativeTo
Indicates that one entity’s level of difficulty is being compared to and expressed in relation to another entity’s level of difficulty.
-
E.
trainingLevel
Indicates the degree or stage of training or skill development that an entity has attained.
- 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_69d807657e8c8190bd9435ee2f823845 |
completed | April 9, 2026, 8:09 p.m. |
| NER | Named-entity recognition | batch_69d97e9828748190b2ad9ea29180b7d3 |
completed | April 10, 2026, 10:50 p.m. |
| PD | Predicate disambiguation | batch_69d97dc153a081909d13a694993f074a |
completed | April 10, 2026, 10:46 p.m. |
Created at: April 9, 2026, 8:47 p.m.