Triple
T21161126
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Benny Wenda |
E521441
|
entity |
| Predicate | hasEscapedFrom |
P11257
|
FINISHED |
| Object | Indonesian custody |
—
|
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: Indonesian custody | Statement: [Benny Wenda, hasEscapedFrom, Indonesian custody]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasEscapedFrom Context triple: [Benny Wenda, hasEscapedFrom, Indonesian custody]
-
A.
escapedBy
Indicates that an entity is freed or enabled to escape through the actions or intervention of another entity.
-
B.
escapeStatus
Indicates whether an entity has escaped, is in the process of escaping, or has not escaped from a given situation or confinement.
-
C.
escapesWith
Indicates that one entity flees or breaks free from a situation, place, or constraint together with another entity as a companion or accomplice.
-
D.
helpedEscape
Indicates that one entity assisted another in getting away from confinement, danger, or pursuit.
-
E.
fledFrom
chosen
Indicates that one entity escaped or ran away from another entity or location.
- 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_69e0b50d1ea481909c07e63c3ead9316 |
completed | April 16, 2026, 10:08 a.m. |
| NER | Named-entity recognition | batch_69e72530e3388190a170c5a2a19dadfc |
completed | April 21, 2026, 7:20 a.m. |
| PD | Predicate disambiguation | batch_69e5f5f8a5bc819081918c7fa8e4496d |
completed | April 20, 2026, 9:46 a.m. |
Created at: April 16, 2026, 2:59 p.m.