Triple
T11309769
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 八幡市 |
E267805
|
entity |
| Predicate | 日本の行政区分コード種別 |
P92063
|
FINISHED |
| Object | 市 |
—
|
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: 市 | Statement: [八幡市, 日本の行政区分コード種別, 市]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: 日本の行政区分コード種別 Context triple: [八幡市, 日本の行政区分コード種別, 市]
-
A.
administrativeCodeSystem
Indicates that there is a system or scheme used to assign and manage administrative codes for organizing or identifying entities or records.
-
B.
districtCode
Indicates that an entity is associated with, or identified by, a specific administrative district code.
-
C.
usesAdministrativeDivisionType
Indicates that one entity employs or applies a particular type of administrative division as part of its territorial or organizational structure.
-
D.
administrativeTerritoryType
chosen
Indicates the classification of an administrative area according to its level or type of territorial governance (e.g., city, county, province).
-
E.
都道府県
Indicates a relationship where an entity is a Japanese prefecture or belongs to/pertains to a specific Japanese prefecture.
- 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_69d6aaca5c24819083db46a30d86cb34 |
completed | April 8, 2026, 7:21 p.m. |
| NER | Named-entity recognition | batch_69d7e9c0b3b88190ac0e3d6a5ad3b9bc |
completed | April 9, 2026, 6:02 p.m. |
| PD | Predicate disambiguation | batch_69d787aa31888190860eecaa80da5b20 |
completed | April 9, 2026, 11:04 a.m. |
Created at: April 8, 2026, 9:32 p.m.