Triple

T13575055
Position Surface form Disambiguated ID Type / Status
Subject Diyala Governorate E324259 entity
Predicate hasCity P316 FINISHED
Object Miqdadiyah
Miqdadiyah is a city in eastern Iraq known for its diverse population and its location within the conflict-affected Diyala region.
 E1048242 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: Miqdadiyah | Statement: [Diyala Governorate, hasCity, Miqdadiyah]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Miqdadiyah
Context triple: [Diyala Governorate, hasCity, Miqdadiyah]
  • A. Marafiq
    Marafiq is a major utility company in Saudi Arabia that provides power and water services to industrial cities such as Jubail.
  • B. المستملي
    المستملي هو أحد رواة صحيح البخاري الذين نقلوا ودوّنوا نص الجامع الصحيح، معتمدًا في ذلك على سماعه المباشر من الإمام البخاري.
  • C. Migadāya
    Migadāya is the Deer Park near Sarnath in India, revered in Buddhism as the site where the Buddha delivered his first sermon and set in motion the Wheel of Dharma.
  • D. Musasir
    Musasir was an ancient Urartian city and religious center in the Armenian Highlands, renowned for its prominent temple dedicated to the god Haldi.
  • E. Muladis
    Muladis were Muslims in medieval Iberia who were originally local Christians that had converted to Islam, often blending Arab-Islamic and Iberian cultural elements.
  • 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: Miqdadiyah
Triple: [Diyala Governorate, hasCity, Miqdadiyah]
Generated description
Miqdadiyah is a city in eastern Iraq known for its diverse population and its location within the conflict-affected Diyala region.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Miqdadiyah
Target entity description: Miqdadiyah is a city in eastern Iraq known for its diverse population and its location within the conflict-affected Diyala region.
  • A. Marafiq
    Marafiq is a major utility company in Saudi Arabia that provides power and water services to industrial cities such as Jubail.
  • B. المستملي
    المستملي هو أحد رواة صحيح البخاري الذين نقلوا ودوّنوا نص الجامع الصحيح، معتمدًا في ذلك على سماعه المباشر من الإمام البخاري.
  • C. Migadāya
    Migadāya is the Deer Park near Sarnath in India, revered in Buddhism as the site where the Buddha delivered his first sermon and set in motion the Wheel of Dharma.
  • D. Musasir
    Musasir was an ancient Urartian city and religious center in the Armenian Highlands, renowned for its prominent temple dedicated to the god Haldi.
  • E. Muladis
    Muladis were Muslims in medieval Iberia who were originally local Christians that had converted to Islam, often blending Arab-Islamic and Iberian cultural elements.
  • 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_69d80769100c819099111274614f5ed2 completed April 9, 2026, 8:09 p.m.
NER Named-entity recognition batch_69dbb02b1f108190a12af382d1de70bb completed April 12, 2026, 2:46 p.m.
NED1 Entity disambiguation (via context triple) batch_69f76bba21f88190b8952fb0879e623d completed May 3, 2026, 3:37 p.m.
NEDg Description generation batch_69f77641e5308190a75bcffeb9bfd7b4 completed May 3, 2026, 4:22 p.m.
NED2 Entity disambiguation (via description) batch_69f7791add908190af69b23a54eb7560 completed May 3, 2026, 4:34 p.m.
Created at: April 9, 2026, 9:48 p.m.