Triple

T3328574
Position Surface form Disambiguated ID Type / Status
Subject Great Khan E69977 entity
Predicate equivalentTitle P6530 FINISHED
Object Qaʾan
Qaʾan is a Mongol imperial title signifying the supreme ruler of the Mongol Empire, comparable to the Great Khan.
E349331 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: Qaʾan | Statement: [Great Khan, equivalentTitle, Qaʾan]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Qaʾan
Context triple: [Great Khan, equivalentTitle, Qaʾan]
  • A. Qaha
    Qaha is a city in Egypt’s Qalyubia Governorate, known for its agricultural production and food-processing industries.
  • B. Qataban
    Qataban was an ancient South Arabian kingdom known for its incense trade and strategic position along key caravan routes in what is now Yemen.
  • C. Al Qara
    Al Qara is a town in southwestern Saudi Arabia located within the mountainous Al Bahah Region.
  • D. Kuqa
    Kuqa is an ancient oasis city in China’s Xinjiang region that historically served as a key Buddhist and Silk Road cultural center in the Tarim Basin.
  • E. Kandia
    Kandia is a remote valley and settlement area located within Pakistan’s Kohistan mountain ranges, known for its rugged terrain and isolated communities.
  • 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: Qaʾan
Triple: [Great Khan, equivalentTitle, Qaʾan]
Generated description
Qaʾan is a Mongol imperial title signifying the supreme ruler of the Mongol Empire, comparable to the Great Khan.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Qaʾan
Target entity description: Qaʾan is a Mongol imperial title signifying the supreme ruler of the Mongol Empire, comparable to the Great Khan.
  • A. Qaha
    Qaha is a city in Egypt’s Qalyubia Governorate, known for its agricultural production and food-processing industries.
  • B. Qataban
    Qataban was an ancient South Arabian kingdom known for its incense trade and strategic position along key caravan routes in what is now Yemen.
  • C. Al Qara
    Al Qara is a town in southwestern Saudi Arabia located within the mountainous Al Bahah Region.
  • D. Kuqa
    Kuqa is an ancient oasis city in China’s Xinjiang region that historically served as a key Buddhist and Silk Road cultural center in the Tarim Basin.
  • E. Kandia
    Kandia is a remote valley and settlement area located within Pakistan’s Kohistan mountain ranges, known for its rugged terrain and isolated communities.
  • 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_69ad85a1829881908942c14075644d0d completed March 8, 2026, 2:20 p.m.
NER Named-entity recognition batch_69adb1708b908190bc5c4122623d9b77 completed March 8, 2026, 5:27 p.m.
NED1 Entity disambiguation (via context triple) batch_69b31a7ec9f48190873d90b678713bad completed March 12, 2026, 7:56 p.m.
NEDg Description generation batch_69b31c368e4c8190a011833fce090a7d completed March 12, 2026, 8:04 p.m.
NED2 Entity disambiguation (via description) batch_69b31d3fa6088190a5abf858c01c25bc completed March 12, 2026, 8:08 p.m.
Created at: March 8, 2026, 3:12 p.m.