Triple

T22734710
Position Surface form Disambiguated ID Type / Status
Subject IAR Brașov E562233 entity
Predicate designed P184 FINISHED
Object IAR 22
The IAR 22 is a Romanian light training aircraft developed by IAR Brașov for basic pilot instruction and general aviation use.
 E1562887 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: IAR 22 | Statement: [IAR Brașov, designed, IAR 22]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: IAR 22
Context triple: [IAR Brașov, designed, IAR 22]
  • A. IAR 15
    The IAR 15 was a Romanian single-seat fighter aircraft developed in the early 1930s as one of the first indigenous designs of the IAR Brașov company.
  • B. IAR 81
    The IAR 81 was a Romanian World War II fighter and ground-attack aircraft designed and built by Industria Aeronautică Română.
  • C. IAR 47
    The IAR 47 was a Romanian World War II reconnaissance and light bomber aircraft developed by Industria Aeronautică Română (IAR).
  • D. IAR 27 trainer aircraft
    The IAR 27 was a Romanian single-engine military trainer aircraft developed in the late 1930s by Industria Aeronautică Română for pilot instruction.
  • E. IAR 99 Șoim
    The IAR 99 Șoim is a Romanian-designed advanced jet trainer and light attack aircraft used primarily for pilot training and close air support missions.
  • 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: IAR 22
Triple: [IAR Brașov, designed, IAR 22]
Generated description
The IAR 22 is a Romanian light training aircraft developed by IAR Brașov for basic pilot instruction and general aviation use.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: IAR 22
Target entity description: The IAR 22 is a Romanian light training aircraft developed by IAR Brașov for basic pilot instruction and general aviation use.
  • A. IAR 15
    The IAR 15 was a Romanian single-seat fighter aircraft developed in the early 1930s as one of the first indigenous designs of the IAR Brașov company.
  • B. IAR 81
    The IAR 81 was a Romanian World War II fighter and ground-attack aircraft designed and built by Industria Aeronautică Română.
  • C. IAR 47
    The IAR 47 was a Romanian World War II reconnaissance and light bomber aircraft developed by Industria Aeronautică Română (IAR).
  • D. IAR 27 trainer aircraft
    The IAR 27 was a Romanian single-engine military trainer aircraft developed in the late 1930s by Industria Aeronautică Română for pilot instruction.
  • E. IAR 99 Șoim
    The IAR 99 Șoim is a Romanian-designed advanced jet trainer and light attack aircraft used primarily for pilot training and close air support missions.
  • 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_69e24550859c81908727d91efc3a81b4 completed April 17, 2026, 2:36 p.m.
NER Named-entity recognition batch_69f1796f030881908e141564d442bd1b completed April 29, 2026, 3:22 a.m.
NED1 Entity disambiguation (via context triple) batch_6a0bca0266b08190976d6fda00720bd3 completed May 19, 2026, 2:25 a.m.
NEDg Description generation batch_6a0bcb094b60819090c7550dad826fac completed May 19, 2026, 2:29 a.m.
NED2 Entity disambiguation (via description) batch_6a0bcb7ccc4881909fe70749449c0e6c completed May 19, 2026, 2:31 a.m.
Created at: April 17, 2026, 3:22 p.m.