Triple
T26767323
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Brian Keenan |
E674974
|
entity |
| Predicate | durationOfDetention |
P161218
|
FINISHED |
| Object | approximately four 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 four years | Statement: [Brian Keenan, durationOfDetention, approximately four years]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: durationOfDetention Context triple: [Brian Keenan, durationOfDetention, approximately four years]
-
A.
detentionDay
Indicates the specific day on which an entity is required to serve or attend detention.
-
B.
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).
-
C.
detentionStartTime
Indicates the specific time at which a period of detention for an entity begins.
-
D.
permittedDetentionPeriod
Indicates the legally allowed duration for which an entity may be held in detention.
-
E.
detainedUntil
Indicates that an entity is held in custody or confinement up to a specified time or until a particular condition is met.
- 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_69eecda85298819097ee1c38a3d772e7 |
completed | April 27, 2026, 2:44 a.m. |
| NER | Named-entity recognition | batch_69f6192a12ac8190a92158e548f4d5c8 |
completed | May 2, 2026, 3:32 p.m. |
| PD | Predicate disambiguation | batch_69f60b8dfa0c8190864e1a940024d0a0 |
completed | May 2, 2026, 2:34 p.m. |
| PDg | Predicate description generation | batch_69f6106d346c8190868489f36c65b6ec |
completed | May 2, 2026, 2:55 p.m. |
Created at: April 27, 2026, 4 a.m.