Triple

T11750067
Position Surface form Disambiguated ID Type / Status
Subject Soko J-22 Orao E279381 entity
Predicate manufacturer P490 FINISHED
Object SOKO
SOKO was a Yugoslav aircraft manufacturer known for producing military and training aircraft, including the Soko J-22 Orao attack jet.
 E944871 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: SOKO | Statement: [Soko J-22 Orao, manufacturer, SOKO]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: SOKO
Context triple: [Soko J-22 Orao, manufacturer, SOKO]
  • A. SOKOM
    SOKOM is the Danish Special Operations Command, the unified headquarters responsible for overseeing Denmark’s elite special operations forces.
  • B. SOK
    SOK is the abbreviation for the Swedish Olympic Committee, the organization responsible for overseeing Sweden's participation in the Olympic Games.
  • C. Saho
    Saho is a Cushitic language spoken primarily by the Saho people in Eritrea and neighboring regions of the Horn of Africa.
  • D. Sukošan
    Sukošan is a coastal village and popular tourist destination on the Adriatic Sea in Croatia, known for its marina and beaches near the city of Zadar.
  • E. Soka
    Soka is a city in Japan known for its location in Saitama Prefecture just north of Tokyo and its traditional rice crackers called "Soka senbei."
  • 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: SOKO
Triple: [Soko J-22 Orao, manufacturer, SOKO]
Generated description
SOKO was a Yugoslav aircraft manufacturer known for producing military and training aircraft, including the Soko J-22 Orao attack jet.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: SOKO
Target entity description: SOKO was a Yugoslav aircraft manufacturer known for producing military and training aircraft, including the Soko J-22 Orao attack jet.
  • A. SOKOM
    SOKOM is the Danish Special Operations Command, the unified headquarters responsible for overseeing Denmark’s elite special operations forces.
  • B. SOK
    SOK is the abbreviation for the Swedish Olympic Committee, the organization responsible for overseeing Sweden's participation in the Olympic Games.
  • C. Saho
    Saho is a Cushitic language spoken primarily by the Saho people in Eritrea and neighboring regions of the Horn of Africa.
  • D. Sukošan
    Sukošan is a coastal village and popular tourist destination on the Adriatic Sea in Croatia, known for its marina and beaches near the city of Zadar.
  • E. Soka
    Soka is a city in Japan known for its location in Saitama Prefecture just north of Tokyo and its traditional rice crackers called "Soka senbei."
  • 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_69d6ab01038c819080714901502c84fc completed April 8, 2026, 7:22 p.m.
NER Named-entity recognition batch_69d8a508b0c4819082fbcc27d559ea2f completed April 10, 2026, 7:21 a.m.
NED1 Entity disambiguation (via context triple) batch_69f01a13550081909a26f57b30d68e03 completed April 28, 2026, 2:23 a.m.
NEDg Description generation batch_69f0319622c48190bee6c906f08c0a8c completed April 28, 2026, 4:03 a.m.
NED2 Entity disambiguation (via description) batch_69f05ad36e4c8190b7239e5b33713369 completed April 28, 2026, 6:59 a.m.
Created at: April 8, 2026, 9:41 p.m.