Triple
T5115672
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kalief Browder |
E115326
|
entity |
| Predicate | detentionDuration |
P8398
|
FINISHED |
| Object | approximately three years |
—
|
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: approximately three years | Statement: [Kalief Browder, detentionDuration, approximately three years]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: detentionDuration Context triple: [Kalief Browder, detentionDuration, approximately three years]
-
A.
detainedFor
Indicates that one entity is being held in custody or confinement because of, or as a consequence of, another entity (such as a reason, charge, or event).
-
B.
detainedUntil
Indicates that an entity is held in custody or confinement up to a specified time or until a particular condition is met.
-
C.
detainedAfter
Indicates that one entity is held in custody or confinement following another specified event or action.
-
D.
detentionType
Indicates the specific category or form of detention applied to an entity within a custodial or restrictive context.
-
E.
durationOfImprisonment
chosen
Indicates the length of time that an entity is or was held in imprisonment.
- 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_69bd4441d1648190a54a533895041987 |
completed | March 20, 2026, 12:57 p.m. |
| NER | Named-entity recognition | batch_69bd75ce6044819094166aebf0688665 |
completed | March 20, 2026, 4:29 p.m. |
| PD | Predicate disambiguation | batch_69bd7160d44081908cc64f3c14d28b81 |
completed | March 20, 2026, 4:10 p.m. |
Created at: March 20, 2026, 1:41 p.m.