Triple

T2221260
Position Surface form Disambiguated ID Type / Status
Subject Nadia Comăneci E48145 entity
Predicate givenName P17 FINISHED
Object Nadia
Nadia is a feminine given name of Slavic origin, best known internationally through the Romanian gymnast Nadia Comăneci.
E246202 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: Nadia | Statement: [Nadia Comăneci, givenName, Nadia]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Nadia
Context triple: [Nadia Comăneci, givenName, Nadia]
  • A. Nina
    Nina is a Danish fashion model best known for her appearances in the Sports Illustrated Swimsuit Issue and various high-profile advertising campaigns.
  • B. Natalia
    Natalia was a short-lived Boer republic established in the 1830s in what is now KwaZulu-Natal, South Africa.
  • C. Gianna
    Gianna is a feminine given name of Italian origin, often associated with the late Gianna Bryant, daughter of basketball legend Kobe Bryant.
  • D. Yelena
    Yelena is a feminine given name of Slavic origin, commonly used in Russian-speaking countries and equivalent to Helen or Helena in English.
  • E. Tanya
    Tanya is the foundational Chabad-Lubavitch Hasidic work by Rabbi Shneur Zalman of Liadi, presenting a systematic approach to Jewish mysticism, psychology, and spiritual self-improvement.
  • 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: Nadia
Triple: [Nadia Comăneci, givenName, Nadia]
Generated description
Nadia is a feminine given name of Slavic origin, best known internationally through the Romanian gymnast Nadia Comăneci.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Nadia
Target entity description: Nadia is a feminine given name of Slavic origin, best known internationally through the Romanian gymnast Nadia Comăneci.
  • A. Nina
    Nina is a Danish fashion model best known for her appearances in the Sports Illustrated Swimsuit Issue and various high-profile advertising campaigns.
  • B. Natalia
    Natalia was a short-lived Boer republic established in the 1830s in what is now KwaZulu-Natal, South Africa.
  • C. Gianna
    Gianna is a feminine given name of Italian origin, often associated with the late Gianna Bryant, daughter of basketball legend Kobe Bryant.
  • D. Yelena
    Yelena is a feminine given name of Slavic origin, commonly used in Russian-speaking countries and equivalent to Helen or Helena in English.
  • E. Tanya
    Tanya is the foundational Chabad-Lubavitch Hasidic work by Rabbi Shneur Zalman of Liadi, presenting a systematic approach to Jewish mysticism, psychology, and spiritual self-improvement.
  • 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_69a88aa1ee708190862c8c378c41e9eb completed March 4, 2026, 7:40 p.m.
NER Named-entity recognition batch_69abc0156c8c819083e3e3b6ede1e951 completed March 7, 2026, 6:05 a.m.
NED1 Entity disambiguation (via context triple) batch_69ae65605fa481908ac5b9d837600626 completed March 9, 2026, 6:14 a.m.
NEDg Description generation batch_69ae669aa29c81909770cd69d27c274c completed March 9, 2026, 6:20 a.m.
NED2 Entity disambiguation (via description) batch_69ae66fb7f1c8190b2bc306f06c423f1 completed March 9, 2026, 6:21 a.m.
Created at: March 4, 2026, 7:47 p.m.