Triple
T35316167
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | USS Keeling |
E1019910
|
entity |
| Predicate | primaryMissionInStory |
P198075
|
FINISHED |
| Object | Atlantic convoy protection |
—
|
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 protection | Statement: [USS Keeling, primaryMissionInStory, Atlantic convoy protection]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: primaryMissionInStory Context triple: [USS Keeling, primaryMissionInStory, Atlantic convoy protection]
-
A.
primaryMissionTo
Indicates that an entity has a main or principal mission directed toward or focused on another entity.
-
B.
primaryMissions
chosen
Indicates the main missions or core objectives assigned to or undertaken by an entity.
-
C.
laterPrimaryMission
Indicates that one mission occurs after another mission in the sequence of primary missions.
-
D.
intendedMission
Indicates that one entity is the planned or designated mission, task, or objective associated with another entity.
-
E.
missionFirst
Indicates that one entity prioritizes accomplishing a mission or objective above other considerations or interests.
- 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_69f76de9d45c81908a2ed0956b448b65 |
completed | May 3, 2026, 3:46 p.m. |
| NER | Named-entity recognition | batch_6a037c8c34f88190ace26f555827f23e |
completed | May 12, 2026, 7:16 p.m. |
| PD | Predicate disambiguation | batch_6a037a0324d08190ac5b610cc0f6a38c |
completed | May 12, 2026, 7:05 p.m. |
Created at: May 3, 2026, 4:03 p.m.