Triple
T37092269
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | HMS Ulysses |
E918454
|
entity |
| Predicate | followsConvoyType |
P50418
|
FINISHED |
| Object | Arctic convoy to the Soviet Union |
—
|
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: Arctic convoy to the Soviet Union | Statement: [HMS Ulysses, followsConvoyType, Arctic convoy to the Soviet Union]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: followsConvoyType Context triple: [HMS Ulysses, followsConvoyType, Arctic convoy to the Soviet Union]
-
A.
convoyType
chosen
Indicates the specific kind or classification of convoy associated with or used in the relationship between the entities.
-
B.
convoyWith
Indicates that one entity is traveling together with another as part of an organized group or convoy, typically for mutual support, protection, or coordination.
-
C.
followsVehicle
Indicates that one vehicle is moving behind and in the same direction as another vehicle, maintaining a following position.
-
D.
convoyCode
Indicates that an entity is assigned or associated with a specific convoy identification code used for grouping or tracking movements.
-
E.
followsShip
Indicates that one entity moves behind and along the path of a ship, maintaining a following position relative to it.
- 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_69f76e9a48bc8190a3947508d8bca408 |
completed | May 3, 2026, 3:49 p.m. |
| NER | Named-entity recognition | batch_69ff5b233e9c8190adc06cca0758986b |
completed | May 9, 2026, 4:04 p.m. |
| PD | Predicate disambiguation | batch_69ff5a5682108190a006b23c4fcdcc7c |
completed | May 9, 2026, 4:01 p.m. |
Created at: May 3, 2026, 4:14 p.m.