Triple
T28813259
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 富山市 |
E727572
|
entity |
| Predicate | 人口集計単位 |
P105946
|
FINISHED |
| Object | 富山市域 |
—
|
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: 富山市域 | Statement: [富山市, 人口集計単位, 富山市域]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: 人口集計単位 Context triple: [富山市, 人口集計単位, 富山市域]
-
A.
populationUnit
Indicates the unit of measurement in which a population quantity is expressed (e.g., individuals, households, families).
-
B.
populationCensusUnit
Indicates that a population count or demographic measurement is taken with respect to a specific census-defined unit or area.
-
C.
statisticalUnitOf
Indicates that one entity serves as the statistical unit (the basic unit of observation or analysis) for which data or statistics are collected or reported about another entity.
-
D.
samplingUnit
Indicates that one entity serves as the basic unit or element from which samples are drawn or measured in a sampling process.
-
E.
statisticalAreaOf
chosen
Indicates that one entity is the designated statistical area or region associated with, containing, or characterizing another entity for statistical or demographic purposes.
- 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_69f0319c38948190bca746ad60fd25ba |
completed | April 28, 2026, 4:03 a.m. |
| NER | Named-entity recognition | batch_69f658f163a88190b1dd222eaa0f93ea |
completed | May 2, 2026, 8:05 p.m. |
| PD | Predicate disambiguation | batch_69f65760fd3081908ffe014a5e2bf069 |
completed | May 2, 2026, 7:58 p.m. |
Created at: April 28, 2026, 6:31 a.m.