Triple
T558058
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Division of Law Enforcement |
E11987
|
entity |
| Predicate | officersHavePower |
P544
|
FINISHED |
| Object | authority to make arrests |
—
|
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: authority to make arrests | Statement: [Division of Law Enforcement, officersHavePower, authority to make arrests]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: officersHavePower Context triple: [Division of Law Enforcement, officersHavePower, authority to make arrests]
-
A.
exercisedPowerOver
Indicates that one entity exerted control, influence, or authority over another entity.
-
B.
powers
Indicates that one entity supplies or provides the energy, authority, or driving force that enables another entity to function or operate.
-
C.
typeOfLawEnforcement
Indicates that one entity is a specific kind or category of law enforcement associated with another entity.
-
D.
grantedPower
Indicates that one entity has conferred authority, control, or a specific capability to another entity.
-
E.
hasPower
chosen
Indicates that one entity possesses authority, control, or influence over another entity or over a particular domain or resource.
- 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_69a4932941d08190815efd422f0b4ca7 |
completed | March 1, 2026, 7:27 p.m. |
| NER | Named-entity recognition | batch_69a499dd84ec81909d2b309da057b9c6 |
completed | March 1, 2026, 7:56 p.m. |
| PD | Predicate disambiguation | batch_69a494bd78e8819083c519669158f209 |
completed | March 1, 2026, 7:34 p.m. |
Created at: March 1, 2026, 7:32 p.m.