Triple
T36128993
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 佐賀城 |
E1044962
|
entity |
| Predicate | 所在地（旧国名） |
P18608
|
FINISHED |
| Object | 肥前国佐賀郡 |
—
|
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: 肥前国佐賀郡 | Statement: [佐賀城, 所在地（旧国名）, 肥前国佐賀郡]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: 所在地（旧国名） Context triple: [佐賀城, 所在地（旧国名）, 肥前国佐賀郡]
-
A.
isLocatedOn
chosen
Indicates that one entity exists at or is situated upon the surface or area of another entity.
-
B.
usedToBeHomelandOf
Indicates that a place previously served as the homeland or native territory of a particular group or entity, but no longer does so.
-
C.
administrativeCenterNowLocatedIn
Indicates that the current administrative center of an entity is located within a specified place or jurisdiction.
-
D.
countryLocatedIn
Indicates that a country is geographically or politically situated within a specified larger region, territory, or entity.
-
E.
hasCountryOfOriginToponym
Indicates that something has a place name (toponym) specifying the country from which it originates.
- 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_69f76e356c908190abc6ca1e6a05b011 |
completed | May 3, 2026, 3:48 p.m. |
| NER | Named-entity recognition | batch_69f7b3e2f3c08190be4fd1ae4fa1266d |
completed | May 3, 2026, 8:45 p.m. |
| PD | Predicate disambiguation | batch_69f7b1bcc47081909fe7d592ac69006c |
completed | May 3, 2026, 8:36 p.m. |
Created at: May 3, 2026, 4:08 p.m.