Triple

T8632275
Position Surface form Disambiguated ID Type / Status
Subject Hovhannes Kajaznuni E204430 entity
Predicate familyName P18 FINISHED
Object Kajaznuni
Kajaznuni is an Armenian surname most notably borne by Hovhannes Kajaznuni, the first Prime Minister of the First Republic of Armenia.
 E747093 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: Kajaznuni | Statement: [Hovhannes Kajaznuni, familyName, Kajaznuni]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Kajaznuni
Context triple: [Hovhannes Kajaznuni, familyName, Kajaznuni]
  • A. Taznatit
    Taznatit is a Berber language whose features have influenced the development and structure of the Korandje language.
  • B. Kusaila
    Kusaila was a 7th-century Berber Christian leader and military commander who led resistance against the early Muslim expansion in North Africa.
  • C. Udjebten
    Udjebten was an ancient Egyptian queen of the Sixth Dynasty, likely one of the principal wives of Pharaoh Pepi II Neferkare.
  • D. Kulisusu
    Kulisusu is a town and administrative center located in the province of Southeast Sulawesi, Indonesia.
  • E. Zakonopravilo
    Zakonopravilo is a medieval Serbian legal and ecclesiastical code compiled by Saint Sava that became the foundational law book of the Serbian Orthodox Church and medieval Serbian state.
  • 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: Kajaznuni
Triple: [Hovhannes Kajaznuni, familyName, Kajaznuni]
Generated description
Kajaznuni is an Armenian surname most notably borne by Hovhannes Kajaznuni, the first Prime Minister of the First Republic of Armenia.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Kajaznuni
Target entity description: Kajaznuni is an Armenian surname most notably borne by Hovhannes Kajaznuni, the first Prime Minister of the First Republic of Armenia.
  • A. Taznatit
    Taznatit is a Berber language whose features have influenced the development and structure of the Korandje language.
  • B. Kusaila
    Kusaila was a 7th-century Berber Christian leader and military commander who led resistance against the early Muslim expansion in North Africa.
  • C. Udjebten
    Udjebten was an ancient Egyptian queen of the Sixth Dynasty, likely one of the principal wives of Pharaoh Pepi II Neferkare.
  • D. Kulisusu
    Kulisusu is a town and administrative center located in the province of Southeast Sulawesi, Indonesia.
  • E. Zakonopravilo
    Zakonopravilo is a medieval Serbian legal and ecclesiastical code compiled by Saint Sava that became the foundational law book of the Serbian Orthodox Church and medieval Serbian state.
  • 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_69ca834b903c8190add96cc651e1a477 completed March 30, 2026, 2:06 p.m.
NER Named-entity recognition batch_69cc4742a89081909f9f7b3621e50b40 completed March 31, 2026, 10:14 p.m.
NED1 Entity disambiguation (via context triple) batch_69cebc13073c8190ad6e92b8f7161739 completed April 2, 2026, 6:57 p.m.
NEDg Description generation batch_69cebd4633f08190971d5d67e5a7496a completed April 2, 2026, 7:02 p.m.
NED2 Entity disambiguation (via description) batch_69cebe12fa94819099e37ed9e5cd83b7 completed April 2, 2026, 7:05 p.m.
Created at: March 30, 2026, 6:27 p.m.