Triple
T22440443
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 半蔵門 |
E554739
|
entity |
| Predicate | 構造的特徴 |
P23657
|
FINISHED |
| Object | 石垣に囲まれた門 |
—
|
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: 石垣に囲まれた門 | Statement: [半蔵門, 構造的特徴, 石垣に囲まれた門]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: 構造的特徴 Context triple: [半蔵門, 構造的特徴, 石垣に囲まれた門]
-
A.
構造種別
Indicates the classification of how something is structured or constructed, distinguishing between different types or forms of structure.
-
B.
constructionCharacteristic
chosen
Indicates a specific structural or material property that characterizes how something is built or constructed.
-
C.
featuresStructure
Indicates that one entity possesses, exhibits, or incorporates a particular structure as a notable characteristic or component.
-
D.
מבנה
Indicates a structural or organizational relationship between entities, where one serves as a framework, configuration, or arrangement for the other.
-
E.
builtStructureFor
Indicates that one entity constructed or assembled a structure specifically intended for the use, benefit, or purpose of another entity.
- 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_69e11e5010e48190ae1e9c9db9697637 |
completed | April 16, 2026, 5:37 p.m. |
| NER | Named-entity recognition | batch_69f15ae1f82881908a611f134eb03f3d |
completed | April 29, 2026, 1:12 a.m. |
| PD | Predicate disambiguation | batch_69e898a327948190beee5e168006a0a7 |
completed | April 22, 2026, 9:45 a.m. |
Created at: April 16, 2026, 8:47 p.m.