Triple
T6780401
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Boven Digoel |
E155665
|
entity |
| Predicate | detentionPolicy |
P72783
|
FINISHED |
| Object | administrative exile without normal legal process |
—
|
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: administrative exile without normal legal process | Statement: [Boven Digoel, detentionPolicy, administrative exile without normal legal process]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: detentionPolicy Context triple: [Boven Digoel, detentionPolicy, administrative exile without normal legal process]
-
A.
preservationPolicy
Indicates the rules or strategy governing how something is maintained, protected, and retained over time.
-
B.
expirationPolicy
Indicates the rules or conditions under which something becomes invalid, unusable, or no longer in effect after a certain time or event.
-
C.
archivePolicy
Indicates the rules or conditions governing how items are stored, retained, and managed in an archive.
-
D.
retentionMethod
Indicates the method or strategy used to retain or keep something (such as data, customers, or resources) over time.
-
E.
agePolicy
Indicates a rule or restriction that specifies how something should be treated or allowed based on the ages of the entities involved.
- 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_69c688162bf8819088b664b5c3b5be7a |
completed | March 27, 2026, 1:37 p.m. |
| NER | Named-entity recognition | batch_69c6d26b32c0819093f86b1002260660 |
completed | March 27, 2026, 6:54 p.m. |
| PD | Predicate disambiguation | batch_69c6d095dcac8190bb9b943f50a7f885 |
completed | March 27, 2026, 6:46 p.m. |
| PDg | Predicate description generation | batch_69c6d182213c819086fcbbfd3d64d80b |
completed | March 27, 2026, 6:50 p.m. |
Created at: March 27, 2026, 2:14 p.m.