Triple
T38533685
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Cannon-class destroyer escort |
E923436
|
entity |
| Predicate | designedMission |
P42909
|
FINISHED |
| Object | Atlantic convoy escort |
—
|
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: Atlantic convoy escort | Statement: [Cannon-class destroyer escort, designedMission, Atlantic convoy escort]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: designedMission Context triple: [Cannon-class destroyer escort, designedMission, Atlantic convoy escort]
-
A.
missionDesign
Indicates the relationship in which an entity plans, structures, and specifies the objectives, constraints, and procedures for carrying out a mission.
-
B.
intendedMission
chosen
Indicates that one entity is the planned or designated mission, task, or objective associated with another entity.
-
C.
typeOfMission
Indicates the specific category or nature of a mission that an entity is associated with or engaged in.
-
D.
missionTo
Indicates that one entity is assigned, directed, or sent to carry out a specific mission involving another entity or location.
-
E.
establishedMissionFor
Indicates that an entity formally created or set up a specific mission, assigning it purpose or objectives.
- 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_69f76ea8f6348190a5c03fb6292bbee3 |
completed | May 3, 2026, 3:50 p.m. |
| NER | Named-entity recognition | batch_69ffaa7bc45c8190b907db8579244a7b |
completed | May 9, 2026, 9:43 p.m. |
| PD | Predicate disambiguation | batch_69ffa9f6c9a481908fbd4d18b311cbe2 |
completed | May 9, 2026, 9:41 p.m. |
Created at: May 3, 2026, 4:32 p.m.