Triple
T26252055
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Major Crime Team (Essex Police) |
E656618
|
entity |
| Predicate | caseSelectionCriterion |
P36177
|
FINISHED |
| Object | seriousness of offense |
—
|
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: seriousness of offense | Statement: [Major Crime Team (Essex Police), caseSelectionCriterion, seriousness of offense]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: caseSelectionCriterion Context triple: [Major Crime Team (Essex Police), caseSelectionCriterion, seriousness of offense]
-
A.
selectionCriteria
Indicates the conditions or rules used to choose certain entities from a larger set.
-
B.
proposesCriterion
Indicates that one entity suggests or puts forward a specific criterion to be considered or used by another entity or within a given context.
-
C.
establishesCriterion
Indicates that an entity defines or sets a standard, rule, or condition by which another entity is to be judged, selected, or evaluated.
-
D.
selectionReason
Indicates the reason or justification for choosing or selecting one entity over alternatives.
-
E.
selectionCharacteristic
chosen
Indicates a distinguishing feature or criterion used to choose or differentiate one entity from others.
- 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_69ee5b4d25ac819086acb51184602576 |
completed | April 26, 2026, 6:37 p.m. |
| NER | Named-entity recognition | batch_69f60dcb59cc819095eda1b1a4947a19 |
completed | May 2, 2026, 2:44 p.m. |
| PD | Predicate disambiguation | batch_69f5f7fd90fc81909055b211368f9139 |
completed | May 2, 2026, 1:11 p.m. |
Created at: April 26, 2026, 9:07 p.m.