Triple
T21837074
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | M927 |
E539146
|
entity |
| Predicate | militaryTruckFamily |
P126221
|
FINISHED |
| Object | 5-ton 6x6 tactical truck |
—
|
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: 5-ton 6x6 tactical truck | Statement: [M927, militaryTruckFamily, 5-ton 6x6 tactical truck]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: militaryTruckFamily Context triple: [M927, militaryTruckFamily, 5-ton 6x6 tactical truck]
-
A.
poweredVehicleFamily
chosen
Indicates that one vehicle is part of a family or group of vehicles that share a common powered (motorized) design or platform.
-
B.
cargoVehicle
Indicates a relationship where a vehicle is used or designated for transporting cargo or goods.
-
C.
isMilitaryVariantOf
Indicates that one entity is a military-specific version or adaptation of another, typically civilian or general-purpose, entity.
-
D.
mechanicalTransport
Indicates a relationship where an entity is moved or carried from one place to another using a mechanical means of transportation (e.g., vehicles, machines, or devices).
-
E.
usesInfantryFightingVehicle
Indicates that an entity employs or operates an infantry fighting vehicle as part of its activities or operations.
- 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_69e0c475cda88190987d08f23caebdc1 |
completed | April 16, 2026, 11:13 a.m. |
| NER | Named-entity recognition | batch_69f0a7a890208190a902184e60194e1c |
completed | April 28, 2026, 12:27 p.m. |
| PD | Predicate disambiguation | batch_69e6be8c14748190bdcc44a14d50bea4 |
completed | April 21, 2026, 12:02 a.m. |
Created at: April 16, 2026, 6:55 p.m.