Triple

T21017967
Position Surface form Disambiguated ID Type / Status
Subject Kayanian dynasty E517729 entity
Predicate hasMember P10 FINISHED
Object Bahman
Bahman is a legendary Kayanian king in Iranian mythology, often associated with the continuation of the royal line after Kay Bahman and linked to early Zoroastrian epic traditions.
 E1467600 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: Bahman | Statement: [Kayanian dynasty, hasMember, Bahman]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Bahman
Context triple: [Kayanian dynasty, hasMember, Bahman]
  • A. Rūzbeh
    Rūzbeh was the original Persian name of Ibn al-Muqaffaʿ, the influential 8th-century translator and prose stylist who helped shape early Arabic literature.
  • B. Parviz
    Parviz is a masculine given name of Persian origin commonly used in Iran and among Persian-speaking communities.
  • C. Bahreman
    Bahreman is a village in Kerman Province, Iran, known primarily as the birthplace of former Iranian president Akbar Hashemi Rafsanjani.
  • D. Reza
    Reza is the given name of Reza Shah Pahlavi, the founder of the Pahlavi dynasty and modernizing monarch of Iran in the early 20th century.
  • E. Abolhassan
    Abolhassan is a Persian given name most notably borne by Abolhassan Banisadr, the first President of the Islamic Republic of Iran.
  • 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: Bahman
Triple: [Kayanian dynasty, hasMember, Bahman]
Generated description
Bahman is a legendary Kayanian king in Iranian mythology, often associated with the continuation of the royal line after Kay Bahman and linked to early Zoroastrian epic traditions.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Bahman
Target entity description: Bahman is a legendary Kayanian king in Iranian mythology, often associated with the continuation of the royal line after Kay Bahman and linked to early Zoroastrian epic traditions.
  • A. Rūzbeh
    Rūzbeh was the original Persian name of Ibn al-Muqaffaʿ, the influential 8th-century translator and prose stylist who helped shape early Arabic literature.
  • B. Parviz
    Parviz is a masculine given name of Persian origin commonly used in Iran and among Persian-speaking communities.
  • C. Bahreman
    Bahreman is a village in Kerman Province, Iran, known primarily as the birthplace of former Iranian president Akbar Hashemi Rafsanjani.
  • D. Reza
    Reza is the given name of Reza Shah Pahlavi, the founder of the Pahlavi dynasty and modernizing monarch of Iran in the early 20th century.
  • E. Abolhassan
    Abolhassan is a Persian given name most notably borne by Abolhassan Banisadr, the first President of the Islamic Republic of Iran.
  • 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_6a0965d103848190af83abb0c239f552 completed May 17, 2026, 6:53 a.m.
NEDg Description generation batch_6a09669ac9988190ba5ec8bcf8dc7eb4 completed May 17, 2026, 6:56 a.m.
NED2 Entity disambiguation (via description) batch_6a0967821ce08190a23d22439c343f49 completed May 17, 2026, 7 a.m.
Created at: April 16, 2026, 1:54 p.m.