Triple

T5385762
Position Surface form Disambiguated ID Type / Status
Subject Rostam E120197 entity
Predicate opponent P437 FINISHED
Object Afrasiab
Afrasiab is a legendary Turanian king and formidable adversary of Iran in the Persian epic Shahnameh.
E517727 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: Afrasiab | Statement: [Rostam, opponent, Afrasiab]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Afrasiab
Context triple: [Rostam, opponent, Afrasiab]
  • A. Tushpa
    Tushpa was the ancient fortified city on the eastern shore of Lake Van that served as the political and cultural center of the Kingdom of Urartu in the early first millennium BCE.
  • B. Sarakhs
    Sarakhs is a historic border city in northeastern Iran, known for its strategic location along ancient trade routes between Iran and Central Asia.
  • C. Balkh
    Balkh is an ancient city in northern Afghanistan, historically a major center of Persian culture, trade, and Islamic scholarship.
  • D. Sheberghan
    Sheberghan is a city in northern Afghanistan that serves as a political and military stronghold of Uzbek leader Abdul Rashid Dostum.
  • E. Khiva
    Khiva is an ancient oasis city in western Uzbekistan renowned for its well-preserved walled old town, Itchan Kala, a UNESCO World Heritage Site.
  • 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: Afrasiab
Triple: [Rostam, opponent, Afrasiab]
Generated description
Afrasiab is a legendary Turanian king and formidable adversary of Iran in the Persian epic Shahnameh.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Afrasiab
Target entity description: Afrasiab is a legendary Turanian king and formidable adversary of Iran in the Persian epic Shahnameh.
  • A. Tushpa
    Tushpa was the ancient fortified city on the eastern shore of Lake Van that served as the political and cultural center of the Kingdom of Urartu in the early first millennium BCE.
  • B. Sarakhs
    Sarakhs is a historic border city in northeastern Iran, known for its strategic location along ancient trade routes between Iran and Central Asia.
  • C. Balkh
    Balkh is an ancient city in northern Afghanistan, historically a major center of Persian culture, trade, and Islamic scholarship.
  • D. Sheberghan
    Sheberghan is a city in northern Afghanistan that serves as a political and military stronghold of Uzbek leader Abdul Rashid Dostum.
  • E. Khiva
    Khiva is an ancient oasis city in western Uzbekistan renowned for its well-preserved walled old town, Itchan Kala, a UNESCO World Heritage Site.
  • 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_69bd46354c648190a38b26f107010a96 completed March 20, 2026, 1:05 p.m.
NER Named-entity recognition batch_69bd86f5a7388190aa4ba2052afca74e completed March 20, 2026, 5:42 p.m.
NED1 Entity disambiguation (via context triple) batch_69bf335b5acc81908c43776b614e9c1a completed March 22, 2026, 12:10 a.m.
NEDg Description generation batch_69bf3497be98819085a7c33ee69064c1 completed March 22, 2026, 12:15 a.m.
NED2 Entity disambiguation (via description) batch_69bf35570404819090e553b7921c4cb8 completed March 22, 2026, 12:18 a.m.
Created at: March 20, 2026, 2:03 p.m.