Triple
T28570361
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Rouge FM |
E722795
|
entity |
| Predicate | listenerDemographic |
P2263
|
FINISHED |
| Object | French-speaking adults in Quebec |
—
|
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: French-speaking adults in Quebec | Statement: [Rouge FM, listenerDemographic, French-speaking adults in Quebec]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: listenerDemographic Context triple: [Rouge FM, listenerDemographic, French-speaking adults in Quebec]
-
A.
hasDemographic
Indicates that an entity is associated with or characterized by a particular demographic group or attribute.
-
B.
involvesDemographic
Indicates that an action, event, or entity is related to, affects, or includes a specific demographic group or population segment.
-
C.
demographics
Indicates the relationship of providing or characterizing statistical information about a population’s attributes, such as age, gender, income, or education.
-
D.
demographicsLabel
chosen
Indicates the categorical demographic group or segment that an entity is associated with or classified under.
-
E.
shareDemographicFeature
Indicates that two or more entities have at least one demographic characteristic in common (such as age group, gender, ethnicity, or similar attributes).
- 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_69f01a5f69d08190ad5c0d2167078dec |
completed | April 28, 2026, 2:24 a.m. |
| NER | Named-entity recognition | batch_69f650924b1c8190978fca7cb865f32a |
completed | May 2, 2026, 7:29 p.m. |
| PD | Predicate disambiguation | batch_69f64cb0d8008190912e1430cfaf92aa |
completed | May 2, 2026, 7:12 p.m. |
Created at: April 28, 2026, 4:09 a.m.