Triple
T973793
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Special Victims Division |
E21003
|
entity |
| Predicate | usesInvestigativeMethods |
P22717
|
FINISHED |
| Object | criminal investigation |
—
|
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: criminal investigation | Statement: [Special Victims Division, usesInvestigativeMethods, criminal investigation]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: usesInvestigativeMethods Context triple: [Special Victims Division, usesInvestigativeMethods, criminal investigation]
-
A.
investigatedBy
Indicates that an entity is the subject of an investigation carried out by another entity.
-
B.
subjectOfInquest
Indicates that an entity is the focus or target of a formal inquest or official investigative proceeding.
-
C.
typeOfInvestigation
Indicates the specific kind or category of investigation being conducted or referred to in the relationship.
-
D.
usedMethodOfKilling
Indicates that one entity employed a particular method or means to carry out a killing of another entity.
-
E.
investigatedEvent
Indicates that an event was the subject of an investigation or inquiry carried out by some agent.
- 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_69a493c2b62c8190b616351789ec47f8 |
completed | March 1, 2026, 7:30 p.m. |
| NER | Named-entity recognition | batch_69a4b45f28f081908d41b2d7f353708d |
completed | March 1, 2026, 9:49 p.m. |
| PD | Predicate disambiguation | batch_69a4b2a6aa2c8190aebba71320ab678f |
completed | March 1, 2026, 9:41 p.m. |
| PDg | Predicate description generation | batch_69a4b38630848190bd3898a4f42018ad |
completed | March 1, 2026, 9:45 p.m. |
Created at: March 1, 2026, 7:40 p.m.