Triple
T4608741
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Charlemagne Division |
E100500
|
entity |
| Predicate | nationalComposition |
P32688
|
FINISHED |
| Object | predominantly French |
—
|
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: predominantly French | Statement: [Charlemagne Division, nationalComposition, predominantly French]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: nationalComposition Context triple: [Charlemagne Division, nationalComposition, predominantly French]
-
A.
religiousCompositionHistorical
Indicates the historical distribution or makeup of religious affiliations within a population or group over time.
-
B.
ethnicConstituency
chosen
Indicates that a political or administrative constituency is defined or characterized primarily by the ethnicity of its population.
-
C.
numberOfEthnicGroupsRepresented
Indicates the count of distinct ethnic groups that are present or represented in a given context or entity.
-
D.
hasPoliticalComposition
Indicates that an entity has a particular political makeup or distribution of political affiliations, parties, or ideologies.
-
E.
populationIncludes
Indicates that a population contains or encompasses the specified individual(s) or subgroup(s) as members or elements.
- 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_69bd43cce1e08190a07d53af6a9b6c24 |
completed | March 20, 2026, 12:55 p.m. |
| NER | Named-entity recognition | batch_69bd599f08d88190ad4bed8bafb592cd |
completed | March 20, 2026, 2:28 p.m. |
| PD | Predicate disambiguation | batch_69bd522e2d5c8190937d0b5574f78f99 |
completed | March 20, 2026, 1:57 p.m. |
Created at: March 20, 2026, 1:12 p.m.