Triple

T21017964
Position Surface form Disambiguated ID Type / Status
Subject Kayanian dynasty E517729 entity
Predicate hasMember P10 FINISHED
Object Kay Lohrasp
Kay Lohrasp is a legendary king in Iranian mythology, traditionally counted among the Kayanian rulers in the epic tradition of the Shahnameh.
E1462860 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: Kay Lohrasp | Statement: [Kayanian dynasty, hasMember, Kay Lohrasp]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Kay Lohrasp
Context triple: [Kayanian dynasty, hasMember, Kay Lohrasp]
  • A. Embeth Davidtz
    Embeth Davidtz is a South African-American actress best known for her role as Helen Hirsch in the acclaimed Holocaust drama "Schindler's List."
  • B. Roslyn Kalloo
    Roslyn Kalloo is a film editor best known for her work on the acclaimed drama "Women Talking."
  • C. Kay Marvis
    Kay Marvis was an American actress best known for her brief film career in the late 1930s and early 1940s and her high-profile marriage to comedian Groucho Marx.
  • D. Kealia Ohai
    Kealia Ohai is an American professional soccer forward known for her standout NWSL career and leadership with the Houston Dash.
  • E. Gwyn Lurie
    Gwyn Lurie is an American screenwriter and filmmaker known for her work on character-driven dramas such as the film "The Music Never Stopped."
  • 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: Kay Lohrasp
Triple: [Kayanian dynasty, hasMember, Kay Lohrasp]
Generated description
Kay Lohrasp is a legendary king in Iranian mythology, traditionally counted among the Kayanian rulers in the epic tradition of the Shahnameh.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Kay Lohrasp
Target entity description: Kay Lohrasp is a legendary king in Iranian mythology, traditionally counted among the Kayanian rulers in the epic tradition of the Shahnameh.
  • A. Embeth Davidtz
    Embeth Davidtz is a South African-American actress best known for her role as Helen Hirsch in the acclaimed Holocaust drama "Schindler's List."
  • B. Roslyn Kalloo
    Roslyn Kalloo is a film editor best known for her work on the acclaimed drama "Women Talking."
  • C. Kay Marvis
    Kay Marvis was an American actress best known for her brief film career in the late 1930s and early 1940s and her high-profile marriage to comedian Groucho Marx.
  • D. Kealia Ohai
    Kealia Ohai is an American professional soccer forward known for her standout NWSL career and leadership with the Houston Dash.
  • E. Gwyn Lurie
    Gwyn Lurie is an American screenwriter and filmmaker known for her work on character-driven dramas such as the film "The Music Never Stopped."
  • 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_69e0b50262b081909bc488937145eb73 completed April 16, 2026, 10:08 a.m.
NER Named-entity recognition batch_69e6fc5a27f08190b26828a6a7b59f7c completed April 21, 2026, 4:26 a.m.
NED1 Entity disambiguation (via context triple) batch_6a093b67103081908033c57e586afa69 completed May 17, 2026, 3:52 a.m.
NEDg Description generation batch_6a0940b362388190a78a244eafa7cbba completed May 17, 2026, 4:14 a.m.
NED2 Entity disambiguation (via description) batch_6a09414912d88190b7da0186ef7b227f completed May 17, 2026, 4:17 a.m.
Created at: April 16, 2026, 1:54 p.m.