Triple

T4607731
Position Surface form Disambiguated ID Type / Status
Subject Himyar E100478 entity
Predicate capital P234 FINISHED
Object Zafar
Zafar was an important ancient South Arabian city that served as the political and cultural center of the Himyarite Kingdom in what is now Yemen.
E458432 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: Zafar | Statement: [Himyar, capital, Zafar]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Zafar
Context triple: [Himyar, capital, Zafar]
  • A. Zafar
    Zafar was the pen name of Bahadur Shah II, the last Mughal emperor of India and a noted Urdu poet.
  • B. Thadiq
    Thadiq is a town in central Saudi Arabia known for its traditional architecture and location within the Riyadh administrative region.
  • C. Zafar Saifullah
    Zafar Saifullah was a senior Indian civil servant who served as Cabinet Secretary and held several key administrative positions in the Government of India.
  • D. Azeem
    Azeem is a wise and skilled Moorish warrior who becomes Robin Hood’s loyal companion in the film "Robin Hood: Prince of Thieves."
  • E. Ilyas
    Ilyas is the Arabic and Quranic form of the prophet Elijah, revered in Islamic tradition as a righteous messenger of God.
  • 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: Zafar
Triple: [Himyar, capital, Zafar]
Generated description
Zafar was an important ancient South Arabian city that served as the political and cultural center of the Himyarite Kingdom in what is now Yemen.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Zafar
Target entity description: Zafar was an important ancient South Arabian city that served as the political and cultural center of the Himyarite Kingdom in what is now Yemen.
  • A. Zafar
    Zafar was the pen name of Bahadur Shah II, the last Mughal emperor of India and a noted Urdu poet.
  • B. Thadiq
    Thadiq is a town in central Saudi Arabia known for its traditional architecture and location within the Riyadh administrative region.
  • C. Zafar Saifullah
    Zafar Saifullah was a senior Indian civil servant who served as Cabinet Secretary and held several key administrative positions in the Government of India.
  • D. Azeem
    Azeem is a wise and skilled Moorish warrior who becomes Robin Hood’s loyal companion in the film "Robin Hood: Prince of Thieves."
  • E. Ilyas
    Ilyas is the Arabic and Quranic form of the prophet Elijah, revered in Islamic tradition as a righteous messenger of God.
  • 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_69bd43cce1e08190a07d53af6a9b6c24 completed March 20, 2026, 12:55 p.m.
NER Named-entity recognition batch_69bd599debdc81909d11d0e871c666bb completed March 20, 2026, 2:28 p.m.
NED1 Entity disambiguation (via context triple) batch_69bdfa725c048190af9eea074197fa32 completed March 21, 2026, 1:54 a.m.
NEDg Description generation batch_69bdfd26fbe08190aa44c4a1cbd83f6a completed March 21, 2026, 2:06 a.m.
NED2 Entity disambiguation (via description) batch_69bdfdc4156081909bf99ae7f72fde23 completed March 21, 2026, 2:09 a.m.
Created at: March 20, 2026, 1:12 p.m.