Triple

T9594950
Position Surface form Disambiguated ID Type / Status
Subject SK-105 Kürassier E231507 entity
Predicate hasVariant P455 FINISHED
Object SK-105A2
The SK-105A2 is an upgraded variant of the Austrian SK-105 Kürassier light tank, featuring improved fire control, optics, and combat capabilities.
 E809651 NE FINISHED

How this triple was built (4 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: SK-105A2 | Statement: [SK-105 Kürassier, hasVariant, SK-105A2]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: SK-105A2
Context triple: [SK-105 Kürassier, hasVariant, SK-105A2]
  • A. SK-105A1
    The SK-105A1 is an upgraded variant of the Austrian SK-105 Kürassier light tank destroyer, featuring improved fire control and combat capabilities.
  • B. A5103
    A5103 is a primary A-road in Manchester, England, providing a key route between the city centre and the M56 motorway.
  • C. A-Spec
    A-Spec is Acura’s sport-oriented trim and styling package that enhances select models with more aggressive design cues and performance-focused features.
  • D. S-101
    S-101 is the International Hydrographic Organization’s modern electronic navigational chart standard designed to support next-generation marine navigation systems.
  • E. A500
    A500 is the common shorthand for the Commodore Amiga 500, a popular late-1980s home computer known for its advanced graphics and sound capabilities.
  • F. None of above. chosen
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
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: SK-105A2
Triple: [SK-105 Kürassier, hasVariant, SK-105A2]
Generated description
The SK-105A2 is an upgraded variant of the Austrian SK-105 Kürassier light tank, featuring improved fire control, optics, and combat capabilities.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: SK-105A2
Target entity description: The SK-105A2 is an upgraded variant of the Austrian SK-105 Kürassier light tank, featuring improved fire control, optics, and combat capabilities.
  • A. SK-105A1
    The SK-105A1 is an upgraded variant of the Austrian SK-105 Kürassier light tank destroyer, featuring improved fire control and combat capabilities.
  • B. A5103
    A5103 is a primary A-road in Manchester, England, providing a key route between the city centre and the M56 motorway.
  • C. A-Spec
    A-Spec is Acura’s sport-oriented trim and styling package that enhances select models with more aggressive design cues and performance-focused features.
  • D. S-101
    S-101 is the International Hydrographic Organization’s modern electronic navigational chart standard designed to support next-generation marine navigation systems.
  • E. A500
    A500 is the common shorthand for the Commodore Amiga 500, a popular late-1980s home computer known for its advanced graphics and sound capabilities.
  • F. None of above. chosen

Provenance (5 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_69ca8482884481908eccdfdf64d6fbf7 completed March 30, 2026, 2:11 p.m.
NER Named-entity recognition batch_69cd9a14fd308190beb8fda5a9e912c7 completed April 1, 2026, 10:20 p.m.
NED1 Entity disambiguation (via context triple) batch_69d1791e330881908a6ad31a5bdbccec completed April 4, 2026, 8:48 p.m.
NEDg Description generation batch_69d179e99d6481909d31145b6e627a29 completed April 4, 2026, 8:51 p.m.
NED2 Entity disambiguation (via description) batch_69d17a3aebfc8190acbe62ac900dd9e7 completed April 4, 2026, 8:53 p.m.
Created at: March 30, 2026, 8:07 p.m.