Triple

T3490191
Position Surface form Disambiguated ID Type / Status
Subject Zanzibar E73708 entity
Predicate ethnicGroup P194 FINISHED
Object Shirazi
The Shirazi are a coastal East African ethnic group of mixed African and Persian ancestry, historically influential in the culture and Islamization of regions like Zanzibar.
 E362981 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: Shirazi | Statement: [Zanzibar, ethnicGroup, Shirazi]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Shirazi
Context triple: [Zanzibar, ethnicGroup, Shirazi]
  • A. Shiraz
    Shiraz is a dark-skinned wine grape variety, also known as Syrah, widely used to produce full-bodied red wines around the world.
  • B. Sabzevar
    Sabzevar is a historic and economically significant city in northeastern Iran, known as a regional center of trade, agriculture, and culture in the Khorasan area.
  • C. Zaranj
    Zaranj is a key border city in southwestern Afghanistan that serves as an important trade and transit hub with neighboring Iran.
  • D. Shirin
    Shirin is a feminine given name of Persian origin, widely used in Iran and other Persian-influenced cultures.
  • E. Parsa
    Parsa is the ancient name of the Persian people and their homeland, from which the ethnonym "Persian" is historically derived.
  • 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: Shirazi
Triple: [Zanzibar, ethnicGroup, Shirazi]
Generated description
The Shirazi are a coastal East African ethnic group of mixed African and Persian ancestry, historically influential in the culture and Islamization of regions like Zanzibar.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Shirazi
Target entity description: The Shirazi are a coastal East African ethnic group of mixed African and Persian ancestry, historically influential in the culture and Islamization of regions like Zanzibar.
  • A. Shiraz
    Shiraz is a dark-skinned wine grape variety, also known as Syrah, widely used to produce full-bodied red wines around the world.
  • B. Sabzevar
    Sabzevar is a historic and economically significant city in northeastern Iran, known as a regional center of trade, agriculture, and culture in the Khorasan area.
  • C. Zaranj
    Zaranj is a key border city in southwestern Afghanistan that serves as an important trade and transit hub with neighboring Iran.
  • D. Shirin
    Shirin is a feminine given name of Persian origin, widely used in Iran and other Persian-influenced cultures.
  • E. Parsa
    Parsa is the ancient name of the Persian people and their homeland, from which the ethnonym "Persian" is historically derived.
  • 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_69ad85cca8d4819088494e9f3340fab5 completed March 8, 2026, 2:21 p.m.
NER Named-entity recognition batch_69adbb94190c8190a81eb41042e51a00 completed March 8, 2026, 6:10 p.m.
NED1 Entity disambiguation (via context triple) batch_69b373bb0e00819087899a394f50295d completed March 13, 2026, 2:17 a.m.
NEDg Description generation batch_69b374bb36548190acd369ccef084907 completed March 13, 2026, 2:21 a.m.
NED2 Entity disambiguation (via description) batch_69b3755597d8819081375fab35b75369 completed March 13, 2026, 2:24 a.m.
Created at: March 8, 2026, 3:18 p.m.