Triple
T28310399
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | GSG 9 |
E713976
|
entity |
| Predicate | typeOfPoliceUnit |
P105319
|
FINISHED |
| Object | federal police unit |
—
|
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: federal police unit | Statement: [GSG 9, typeOfPoliceUnit, federal police unit]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: typeOfPoliceUnit Context triple: [GSG 9, typeOfPoliceUnit, federal police unit]
-
A.
policeUnit
Indicates that one entity is a police unit (such as a department, squad, or division) associated with or responsible for another entity.
-
B.
policeDepartmentType
chosen
Indicates the specific organizational category or classification of a police department (e.g., municipal, state, federal).
-
C.
policeBranchType
Indicates the specific organizational category or type of a police branch within a law enforcement structure.
-
D.
patrolType
Indicates the specific kind or category of patrol activity being carried out or assigned.
-
E.
policeClassification
Indicates a categorization relationship where an entity is assigned a specific classification or status by a police or law-enforcement authority.
- 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_69efb5256afc8190b9322d25c3ae6320 |
completed | April 27, 2026, 7:12 p.m. |
| NER | Named-entity recognition | batch_69fe7bfc94bc81909eeec946e8c1c450 |
completed | May 9, 2026, 12:12 a.m. |
| PD | Predicate disambiguation | batch_69fe7b74a1188190886f128e07f712da |
completed | May 9, 2026, 12:10 a.m. |
Created at: April 27, 2026, 11:40 p.m.