Triple
T3965153
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | MG 81 |
E92197
|
entity |
| Predicate | firingPrinciple |
P38751
|
FINISHED |
| Object | automatic recoil operation |
—
|
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: automatic recoil operation | Statement: [MG 81, firingPrinciple, automatic recoil operation]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: firingPrinciple Context triple: [MG 81, firingPrinciple, automatic recoil operation]
-
A.
fireModes
Indicates the different ways or settings in which a weapon or device can be fired or operated.
-
B.
formationPrinciple
Indicates the underlying rule, pattern, or principle according to which something is formed, structured, or brought into existence.
-
C.
activationMechanism
chosen
Indicates the process or method by which one entity initiates, triggers, or enables the activity or functioning of another entity.
-
D.
triggeredFires
Indicates that one entity caused or initiated the occurrence of one or more fires in another entity or location.
-
E.
typeOfPrinciples
Indicates a relationship where one entity specifies the kind or category of principles that another entity embodies, uses, or is governed by.
- 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_69aed96624188190ac8c45bb57ab72b5 |
completed | March 9, 2026, 2:29 p.m. |
| NER | Named-entity recognition | batch_69aefba878a48190a2e234d775215938 |
completed | March 9, 2026, 4:56 p.m. |
| PD | Predicate disambiguation | batch_69aef8efcf3c81908ccf61d9ce26b0c0 |
completed | March 9, 2026, 4:44 p.m. |
Created at: March 9, 2026, 3:31 p.m.