Triple

T6248900
Position Surface form Disambiguated ID Type / Status
Subject Sonya Levien E139994 entity
Predicate familyName P18 FINISHED
Object Levien
Levien is a surname shared by various notable individuals across fields such as literature, film, and business.
 E582269 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: Levien | Statement: [Sonya Levien, familyName, Levien]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Levien
Context triple: [Sonya Levien, familyName, Levien]
  • A. Levar
    Levar is the given name of Levar Stoney, an American politician who has served as the mayor of Richmond, Virginia.
  • B. Leisi
    Leisi is a small settlement located on the island of Saaremaa in western Estonia.
  • C. Leova
    Leova is a small town in southwestern Moldova known for its location near the border with Romania and its position along the Prut River.
  • D. Lavant
    Lavant is a notable high-speed corner on the historic Goodwood Motor Circuit in West Sussex, England.
  • E. Eliassen
    Eliassen is a Norwegian surname borne by various notable figures, including scientists, athletes, and public personalities.
  • 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: Levien
Triple: [Sonya Levien, familyName, Levien]
Generated description
Levien is a surname shared by various notable individuals across fields such as literature, film, and business.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Levien
Target entity description: Levien is a surname shared by various notable individuals across fields such as literature, film, and business.
  • A. Levar
    Levar is the given name of Levar Stoney, an American politician who has served as the mayor of Richmond, Virginia.
  • B. Leisi
    Leisi is a small settlement located on the island of Saaremaa in western Estonia.
  • C. Leova
    Leova is a small town in southwestern Moldova known for its location near the border with Romania and its position along the Prut River.
  • D. Lavant
    Lavant is a notable high-speed corner on the historic Goodwood Motor Circuit in West Sussex, England.
  • E. Eliassen
    Eliassen is a Norwegian surname borne by various notable figures, including scientists, athletes, and public personalities.
  • 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_69c008b4858c819095b0199114a9a87b completed March 22, 2026, 3:20 p.m.
NER Named-entity recognition batch_69c0633c5f2081909b0246e061f8a7d9 completed March 22, 2026, 9:46 p.m.
NED1 Entity disambiguation (via context triple) batch_69c5191d2d248190b34edca246ee74b8 completed March 26, 2026, 11:31 a.m.
NEDg Description generation batch_69c51ac2c2f88190a4e12725a5044fa9 completed March 26, 2026, 11:38 a.m.
NED2 Entity disambiguation (via description) batch_69c582c674e0819083b3d5c4c7eb7826 completed March 26, 2026, 7:02 p.m.
Created at: March 22, 2026, 4:24 p.m.