Triple
T9612461
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Office of Police Complaints of the District of Columbia |
E232134
|
entity |
| Predicate | complaintsSubject |
P450
|
FINISHED |
| Object | use of force |
—
|
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: use of force | Statement: [Office of Police Complaints of the District of Columbia, complaintsSubject, use of force]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: complaintsSubject Context triple: [Office of Police Complaints of the District of Columbia, complaintsSubject, use of force]
-
A.
warningSubject
Indicates that one entity is the topic or focus of a warning issued by another entity.
-
B.
finalReportSubject
Indicates that an entity serves as the main topic or focus of a final report.
-
C.
subjectMatter
chosen
Indicates the topic, theme, or content area that something (such as a work, document, or discussion) is about.
-
D.
complaintsProcedure
Indicates the formal process or mechanism through which complaints are submitted, handled, and resolved.
-
E.
complainant
Indicates that an entity is the person or party who makes a complaint or brings a grievance against 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_69ca8485a90c819094fe40b42fde9d70 |
completed | March 30, 2026, 2:11 p.m. |
| NER | Named-entity recognition | batch_69cd9a8885f88190887843e0fb32a5f3 |
completed | April 1, 2026, 10:22 p.m. |
| PD | Predicate disambiguation | batch_69ccd5a6fd2481908efd131e207b8143 |
completed | April 1, 2026, 8:21 a.m. |
Created at: March 30, 2026, 8:09 p.m.