Triple

T10084755
Position Surface form Disambiguated ID Type / Status
Subject Theodora Asanina E215190 entity
Predicate familyName P18 FINISHED
Object Asanina
Asanina is a Byzantine noble family name associated with the influential Asen (Asan) dynasty.
 E841010 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: Asanina | Statement: [Theodora Asanina, familyName, Asanina]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Asanina
Context triple: [Theodora Asanina, familyName, Asanina]
  • A. Asan
    Asan is a city in South Korea known for its hot springs, historical sites, and growing role as an industrial and educational center.
  • B. Anisy
    Anisy is a small commune in the Calvados department of the Normandy region in northwestern France.
  • C. Anara
    Anara is a town in West Bengal, India, known as the birthplace of acclaimed filmmaker and poet Buddhadeb Dasgupta.
  • D. Araniko
    Araniko was a renowned 13th-century Nepalese architect and artist best known for introducing Newar-style Buddhist architecture to the Yuan dynasty in China.
  • E. Aasai
    Aasai is a 1995 Tamil romantic thriller film that gained widespread recognition for its gripping storyline and for significantly boosting actor Ajith Kumar’s early career.
  • 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: Asanina
Triple: [Theodora Asanina, familyName, Asanina]
Generated description
Asanina is a Byzantine noble family name associated with the influential Asen (Asan) dynasty.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Asanina
Target entity description: Asanina is a Byzantine noble family name associated with the influential Asen (Asan) dynasty.
  • A. Asan
    Asan is a city in South Korea known for its hot springs, historical sites, and growing role as an industrial and educational center.
  • B. Anisy
    Anisy is a small commune in the Calvados department of the Normandy region in northwestern France.
  • C. Anara
    Anara is a town in West Bengal, India, known as the birthplace of acclaimed filmmaker and poet Buddhadeb Dasgupta.
  • D. Araniko
    Araniko was a renowned 13th-century Nepalese architect and artist best known for introducing Newar-style Buddhist architecture to the Yuan dynasty in China.
  • E. Aasai
    Aasai is a 1995 Tamil romantic thriller film that gained widespread recognition for its gripping storyline and for significantly boosting actor Ajith Kumar’s early career.
  • 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_69ca83a1eed081908b2e9580f2ebeea7 completed March 30, 2026, 2:07 p.m.
NER Named-entity recognition batch_69cdd044c1ec8190b5b48cdb0584d00c completed April 2, 2026, 2:11 a.m.
NED1 Entity disambiguation (via context triple) batch_69d2b68188c48190ac783cdfc072c502 completed April 5, 2026, 7:22 p.m.
NEDg Description generation batch_69d2b7aecdb081909f651c1bc1bcfd75 completed April 5, 2026, 7:27 p.m.
NED2 Entity disambiguation (via description) batch_69d2b86bf8948190a79046efadc4adea completed April 5, 2026, 7:30 p.m.
Created at: March 30, 2026, 9 p.m.