Triple
T31518747
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Task Force 22 |
E804146
|
entity |
| Predicate | taskGroup22.3Type |
P55918
|
FINISHED |
| Object | hunter-killer group |
—
|
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: hunter-killer group | Statement: [Task Force 22, taskGroup22.3Type, hunter-killer group]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: taskGroup22.3Type Context triple: [Task Force 22, taskGroup22.3Type, hunter-killer group]
-
A.
taskType
chosen
Indicates the specific category or kind of task an action or assignment belongs to within a broader set of tasks.
-
B.
hasTaskGroup
Indicates that an entity is associated with, or belongs to, a specific task group that organizes or groups related tasks.
-
C.
group3Subject
Indicates that an entity serves as the subject (main actor or topic) within the third group in a grouped or partitioned structure.
-
D.
subgroupCategory
Indicates that one category functions as a more specific subgroup within the scope of another, broader category.
-
E.
workingGroup
Indicates that multiple entities collaborate as a designated team or committee to work together toward a shared task, project, or objective.
- 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_69f348cf839c81908657048402f7f97b |
completed | April 30, 2026, 12:19 p.m. |
| NER | Named-entity recognition | batch_69f6abaa1f648190b77073771df3bf3b |
completed | May 3, 2026, 1:58 a.m. |
| PD | Predicate disambiguation | batch_69f6aa1e84b88190b025f6ca40f17a8a |
completed | May 3, 2026, 1:51 a.m. |
Created at: April 30, 2026, 9:54 p.m.