Triple

T25708726
Position Surface form Disambiguated ID Type / Status
Subject Volkspolizei E644669 entity
Predicate usedVehicleModel P159190 FINISHED
Object Barkas vans
Barkas vans were compact East German light commercial vehicles widely used for transport and service duties across the GDR.
 E1689446 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: Barkas vans | Statement: [Volkspolizei, usedVehicleModel, Barkas vans]
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: Barkas vans
Triple: [Volkspolizei, usedVehicleModel, Barkas vans]
Generated description
Barkas vans were compact East German light commercial vehicles widely used for transport and service duties across the GDR.
PD Predicate disambiguation gpt-5-mini-2025-08-07 
Target predicate: usedVehicleModel
Context triple: [Volkspolizei, usedVehicleModel, Barkas vans]
  • A. usedVehicleModel chosen
    Indicates that a vehicle is a pre-owned (used) instance of a particular vehicle model.
  • B. carModel
    Indicates the specific model designation of a car within a particular make or brand.
  • C. vehicleUsed
    Indicates that a particular vehicle is utilized or employed in performing an action, event, or activity.
  • D. vehicleName
    Indicates the specific name or designation assigned to a vehicle.
  • E. usedAsVehicleFor
    Indicates that one entity functions as a means of transportation or conveyance for another entity.
  • F. None of above.

Provenance (6 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_69e77e83c8ec8190bf52fcdac4838984 completed April 21, 2026, 1:41 p.m.
NER Named-entity recognition batch_69f5fc1385c4819082eff6432380dd2c completed May 2, 2026, 1:28 p.m.
NED1 Entity disambiguation (via context triple) batch_6a10c170627881909c09a859450a22fe completed May 22, 2026, 8:49 p.m.
NEDg Description generation batch_6a10c2489ee48190a35add76cdf94b8b completed May 22, 2026, 8:53 p.m.
NED2 Entity disambiguation (via description) batch_6a10c30975b08190b22c052dab147afe completed May 22, 2026, 8:56 p.m.
PD Predicate disambiguation batch_69f4a0f7c6008190ae8cee3e71e19b94 completed May 1, 2026, 12:47 p.m.
Created at: April 21, 2026, 9:08 p.m.