Triple
T2259233
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ever Given |
E49997
|
entity |
| Predicate | detainedUntil |
P36798
|
FINISHED |
| Object | 2021-07-07 |
—
|
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: 2021-07-07 | Statement: [Ever Given, detainedUntil, 2021-07-07]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: detainedUntil Context triple: [Ever Given, detainedUntil, 2021-07-07]
-
A.
detainedAfter
Indicates that one entity is held in custody or confinement following another specified event or action.
-
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.
detainedBy
Indicates that an entity is being held in custody or confinement by another entity, typically an authority or controlling party.
-
D.
detentionEvent
Indicates an event in which an entity is formally held, confined, or kept in custody, typically by an authority, for a period of time.
-
E.
detentionOperationsBegan
Indicates that the process or activities related to detaining individuals were initiated or commenced.
- 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_69a88b01e0048190ba96431b5f990ba9 |
completed | March 4, 2026, 7:41 p.m. |
| NER | Named-entity recognition | batch_69abc15ad06c8190b6d0babc17015787 |
completed | March 7, 2026, 6:10 a.m. |
| PD | Predicate disambiguation | batch_69abbdb34c148190b51e99f540f97204 |
completed | March 7, 2026, 5:54 a.m. |
| PDg | Predicate description generation | batch_69abbe86dbcc81908c72793af8fe2a4d |
completed | March 7, 2026, 5:58 a.m. |
Created at: March 4, 2026, 7:48 p.m.