Triple
T26551427
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 福岡県太宰府市 |
E671686
|
entity |
| Predicate | 関連する古代官衙 |
P160631
|
FINISHED |
| Object | 大宰府 |
—
|
NE NERFINISHED |
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: 大宰府 | Statement: [福岡県太宰府市, 関連する古代官衙, 大宰府]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: 関連する古代官衙 Context triple: [福岡県太宰府市, 関連する古代官衙, 大宰府]
-
A.
関連施設
Indicates a relationship where one facility is associated with, connected to, or otherwise related to another facility.
-
B.
militaryRelatedOffice
Indicates that an office, position, or role is associated with, derived from, or functionally connected to the military or armed forces.
-
C.
associatedWithFeudalOffice
Indicates a relationship where an entity is linked to, holds, or is otherwise connected with a specific feudal office or position within a feudal system.
-
D.
関連城郭
Indicates a relationship where something is associated with or related to a particular castle or fortification.
-
E.
governingOffice
Indicates the official position or office through which an entity exercises governing authority over a jurisdiction or organization.
- F. None of above. chosen
Provenance (4 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_69eeb32163f08190af5f81282738e27a |
completed | April 27, 2026, 12:51 a.m. |
| NER | Named-entity recognition | batch_69f614624c80819084f6febf57f86828 |
completed | May 2, 2026, 3:12 p.m. |
| PD | Predicate disambiguation | batch_69f602d7b1b0819095ddd3b5169f8ce2 |
completed | May 2, 2026, 1:57 p.m. |
| PDg | Predicate description generation | batch_69f6037bf7a081908862a8359be80cf8 |
completed | May 2, 2026, 2 p.m. |
Created at: April 27, 2026, 1:47 a.m.