Triple
T23112337
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | District Public Prosecutors Office |
E576352
|
entity |
| Predicate | mayApplyFor |
P32549
|
FINISHED |
| Object | pre-trial detention |
—
|
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: pre-trial detention | Statement: [District Public Prosecutors Office, mayApplyFor, pre-trial detention]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: mayApplyFor Context triple: [District Public Prosecutors Office, mayApplyFor, pre-trial detention]
-
A.
mayApply
Indicates that an entity is permitted or eligible to submit or use something (such as a rule, action, or resource) under certain conditions.
-
B.
canApplyFor
chosen
Indicates that one entity has the eligibility or permission to submit a request or application for another entity or opportunity.
-
C.
appliedFor
Indicates that an entity has submitted a request or application to another entity for a position, service, benefit, or opportunity.
-
D.
mayProvideEligibilityFor
Indicates that one entity can serve as a basis or qualifying factor that makes another entity eligible for something (such as a benefit, status, or action).
-
E.
mayTake
Indicates that an entity is permitted or allowed to take, enroll in, or participate in another entity (such as a course, resource, or opportunity).
- 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_69e245f4af548190898d434a64a1e774 |
completed | April 17, 2026, 2:38 p.m. |
| NER | Named-entity recognition | batch_69f18e100d408190a7349563235640d5 |
completed | April 29, 2026, 4:50 a.m. |
| PD | Predicate disambiguation | batch_69ef89f020588190b43393e048e7eda3 |
completed | April 27, 2026, 4:08 p.m. |
Created at: April 17, 2026, 3:58 p.m.