Triple
T13857046
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | CPGE |
E333092
|
entity |
| Predicate | workloadCharacteristic |
P89574
|
FINISHED |
| Object | very heavy workload |
—
|
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: very heavy workload | Statement: [CPGE, workloadCharacteristic, very heavy workload]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: workloadCharacteristic Context triple: [CPGE, workloadCharacteristic, very heavy workload]
-
A.
runtimeCharacteristic
Indicates a relationship where a system, process, or component is associated with a property or behavior that specifically manifests during its execution or operation time.
-
B.
runtimeOfWork
Indicates the duration of time required to complete a particular work or task.
-
C.
laborForceCharacteristic
Indicates a relationship where an entity is described or classified by a specific attribute or status related to its participation in the labor force.
-
D.
operationalCharacteristic
chosen
Indicates a relationship where a specific functional or performance trait is attributed to, or used to describe, how an entity operates.
-
E.
workCharacter
Indicates that a person is a fictional or narrative character appearing in a particular creative work.
- 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_69d81c5ba13c8190839315f54768acfd |
completed | April 9, 2026, 9:38 p.m. |
| NER | Named-entity recognition | batch_69de02dc9f488190b7181dcb7e304632 |
completed | April 14, 2026, 9:03 a.m. |
| PD | Predicate disambiguation | batch_69dbc8691b608190a25a7c70a366b170 |
completed | April 12, 2026, 4:29 p.m. |
Created at: April 9, 2026, 10:14 p.m.