Triple
T22440481
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 乾門 |
E554740
|
entity |
| Predicate | 安全管理 |
P1491
|
FINISHED |
| Object | 警備が厳重な出入口 |
—
|
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: 警備が厳重な出入口 | Statement: [乾門, 安全管理, 警備が厳重な出入口]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: 安全管理 Context triple: [乾門, 安全管理, 警備が厳重な出入口]
-
A.
securityProgram
chosen
Indicates that an entity is associated with, participates in, or is governed by a security program, such as a set of policies, controls, or initiatives related to safety or protection.
-
B.
securityPillar
Indicates that one entity functions as a foundational security pillar or core security domain in relation to another entity.
-
C.
securityOperation
Indicates an action or process carried out to protect, monitor, or defend assets, systems, or environments from threats or unauthorized activities.
-
D.
security
Indicates that an entity provides protection, safety measures, or safeguards to another entity or against specific threats or risks.
-
E.
securityApparatusControl
Indicates that one entity exercises authority over, manages, or directs the operations and decisions of a security or law-enforcement apparatus.
- 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.