Triple
T31629162
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kru people |
E807112
|
entity |
| Predicate | demographyCountry |
P26617
|
FINISHED |
| Object | significant minority in Liberia |
—
|
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: significant minority in Liberia | Statement: [Kru people, demographyCountry, significant minority in Liberia]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: demographyCountry Context triple: [Kru people, demographyCountry, significant minority in Liberia]
-
A.
demographicScope
Indicates the specific population group or demographic segment to which something (e.g., a policy, study, product, or service) is targeted or applicable.
-
B.
countryWithKeyPopulation
chosen
Indicates that a country has a specific, particularly important or target population group that is being identified or highlighted.
-
C.
populationDistributionCountry
Indicates how a country’s population is spread or allocated across its internal regions, groups, or categories.
-
D.
hasPopulationCountry
Indicates that a specified population size is associated with, or belongs to, a particular country.
-
E.
countryPopulationContext
Indicates the contextual population characteristics or statistics associated with a specific country.
- 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_69f348d892948190915f8facacb9568c |
completed | April 30, 2026, 12:19 p.m. |
| NER | Named-entity recognition | batch_69f6b49436b0819094e21603054d05d4 |
completed | May 3, 2026, 2:36 a.m. |
| PD | Predicate disambiguation | batch_69f6b3a7bdb481908d16a32f49e38c2c |
completed | May 3, 2026, 2:32 a.m. |
Created at: April 30, 2026, 10:44 p.m.