Triple
T31012872
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Underwater Offence Group Command |
E790252
|
entity |
| Predicate | isTrainedIn |
P96696
|
FINISHED |
| Object | close-quarters combat |
—
|
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: close-quarters combat | Statement: [Underwater Offence Group Command, isTrainedIn, close-quarters combat]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: isTrainedIn Context triple: [Underwater Offence Group Command, isTrainedIn, close-quarters combat]
-
A.
isTrainedBy
Indicates that one entity receives training, instruction, or coaching from another entity.
-
B.
hasTrainedAt
Indicates that an entity has received training, education, or instruction at a specified place or institution.
-
C.
trainedAs
Indicates that one entity has received education or instruction to perform the role, profession, or function represented by another entity.
-
D.
receivedTrainingIn
chosen
Indicates that one entity has undergone or been provided with training or instruction in a particular field, skill, or subject associated with another entity.
-
E.
hasTrainingFor
Indicates that an entity has received or possesses training that prepares it for performing a specific task, role, or function.
- 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_69f224c73ca48190a1e46cb58ad4045b |
completed | April 29, 2026, 3:33 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 29, 2026, 8:57 p.m.