Triple
T34543611
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | CartoCSS |
E886865
|
entity |
| Predicate | featureSelectionMechanism |
P36177
|
FINISHED |
| Object | filters on feature attributes |
—
|
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: filters on feature attributes | Statement: [CartoCSS, featureSelectionMechanism, filters on feature attributes]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: featureSelectionMechanism Context triple: [CartoCSS, featureSelectionMechanism, filters on feature attributes]
-
A.
selectionMetric
Indicates the criterion or measure used to evaluate and choose among alternative options or candidates.
-
B.
selectionCharacteristic
chosen
Indicates a distinguishing feature or criterion used to choose or differentiate one entity from others.
-
C.
selectionImportance
Indicates that one option in a set is prioritized or weighted more heavily than others during a selection or decision process.
-
D.
featuresMethod
Indicates that an entity includes or provides a particular method as part of its functionality or behavior.
-
E.
featuresSampling
Indicates that an entity includes or employs a particular method or configuration for sampling.
- 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_69f349ce5eb881909e431c670944aa68 |
completed | April 30, 2026, 12:23 p.m. |
| NER | Named-entity recognition | batch_6a0340784c488190aa6c7c9be2e8a434 |
completed | May 12, 2026, 3 p.m. |
| PD | Predicate disambiguation | batch_6a033f33eddc819091507716f6ed7d7d |
completed | May 12, 2026, 2:54 p.m. |
Created at: May 1, 2026, 2:02 a.m.