Triple

T24536068
Position Surface form Disambiguated ID Type / Status
Subject Soviet automotive industry E606952 entity
Predicate mainMilitaryTruckProducer P156647 FINISHED
Object UralAZ
UralAZ is a Russian heavy truck manufacturer best known for producing rugged off-road and military transport vehicles, particularly during the Soviet era.
 E1639259 NE FINISHED

How this triple was built (3 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: UralAZ | Statement: [Soviet automotive industry, mainMilitaryTruckProducer, UralAZ]
NEDg Description generation gpt-5.1
Instruction
Generate a one-sentence description of the target entity. 
You are given a context triple in the form (subject, predicate, object), where the object is the target entity. 
# Instructions
Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. 
Avoid repeating the information from the triple, unless really essential.
# Response Format
Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: UralAZ
Triple: [Soviet automotive industry, mainMilitaryTruckProducer, UralAZ]
Generated description
UralAZ is a Russian heavy truck manufacturer best known for producing rugged off-road and military transport vehicles, particularly during the Soviet era.
PD Predicate disambiguation gpt-5-mini-2025-08-07 
Target predicate: mainMilitaryTruckProducer
Context triple: [Soviet automotive industry, mainMilitaryTruckProducer, UralAZ]
  • A. isMilitaryVariantOf
    Indicates that one entity is a military-specific version or adaptation of another, typically civilian or general-purpose, entity.
  • B. isMilitaryAssetOf
    Indicates that something functions as a military resource, equipment, or facility that belongs to, is controlled by, or is used by a particular entity.
  • C. cargoVehicle
    Indicates a relationship where a vehicle is used or designated for transporting cargo or goods.
  • D. militaryCargoOnBoard
    Indicates that a vehicle, vessel, or aircraft is currently carrying military-related cargo on board.
  • E. typicalLogisticsCombatElement
    Indicates that one entity is a standard or representative logistics combat element typically associated with, or employed by, another entity.
  • F. None of above. chosen

Provenance (7 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_69e2c4c90c848190b23c4303620dcaaf completed April 17, 2026, 11:39 p.m.
NER Named-entity recognition batch_69f2be044d4c819094e14eda28d371a7 completed April 30, 2026, 2:27 a.m.
NED1 Entity disambiguation (via context triple) batch_6a0feea183d081908450a93ed32a6009 completed May 22, 2026, 5:50 a.m.
NEDg Description generation batch_6a0ff0c57b088190b031ea186a987e32 completed May 22, 2026, 5:59 a.m.
NED2 Entity disambiguation (via description) batch_6a0ff16636008190a4267f6b8d8e3bb2 completed May 22, 2026, 6:02 a.m.
PD Predicate disambiguation batch_69f2a6b0ca8081908d931aec560eae56 completed April 30, 2026, 12:47 a.m.
PDg Predicate description generation batch_69f2b8b8bc5881908df49c0b07110246 completed April 30, 2026, 2:04 a.m.
Created at: April 18, 2026, 2:26 a.m.