Triple
T38215226
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ukrainian tugboat Yany Kapu |
E1010665
|
entity |
| Predicate | crewStatusAfterSeizure |
P190300
|
FINISHED |
| Object | crew detained in Russia |
—
|
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: crew detained in Russia | Statement: [Ukrainian tugboat Yany Kapu, crewStatusAfterSeizure, crew detained in Russia]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: crewStatusAfterSeizure Context triple: [Ukrainian tugboat Yany Kapu, crewStatusAfterSeizure, crew detained in Russia]
-
A.
methodOfSeizure
Indicates the manner or technique by which something is taken, captured, or seized.
-
B.
seizureContext
Indicates the situational or clinical circumstances under which a seizure occurs or is observed.
-
C.
dateOfSeizure
Indicates the specific date on which a seizure (such as confiscation or legal taking of property) occurred.
-
D.
seizureCompleted
Indicates that a previously initiated seizure (e.g., of property, assets, or items) has been fully carried out and brought to completion.
-
E.
hasTypicalSeizureType
Indicates that an entity is associated with or characterized by a particular usual or predominant type of seizure.
- 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_69f76dcdc7708190a5f1751d53f40ffe |
completed | May 3, 2026, 3:46 p.m. |
| NER | Named-entity recognition | batch_69fcc42cbac48190b8d3e4c9ce140838 |
completed | May 7, 2026, 4:56 p.m. |
| PD | Predicate disambiguation | batch_69fcb0fc69c88190800453eb57a7e62c |
completed | May 7, 2026, 3:34 p.m. |
| PDg | Predicate description generation | batch_69fcc42b9334819099929649b7ef68ea |
completed | May 7, 2026, 4:56 p.m. |
Created at: May 3, 2026, 4:30 p.m.