Triple

T22773302
Position Surface form Disambiguated ID Type / Status
Subject Madā’in E563615 entity
Predicate hasPart P35 FINISHED
Object al-Mahūza
al-Mahūza was a district within the ancient city complex of Madā’in, historically known as a significant urban quarter in the region of lower Mesopotamia.
E1552941 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: al-Mahūza | Statement: [Madā’in, hasPart, al-Mahūza]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: al-Mahūza
Context triple: [Madā’in, hasPart, al-Mahūza]
  • A. Al-Mahawil
    Al-Mahawil is a town in central Iraq located within the historically significant Babylon Governorate.
  • B. Al-Mughraqa
    Al-Mughraqa is a Palestinian town in the central Gaza Strip, situated south of Gaza City and characterized by its predominantly agricultural community.
  • C. Al-Muzahimiyah
    Al-Muzahimiyah is a town in central Saudi Arabia that serves as a growing satellite community west of Riyadh.
  • D. El Husseiniya
    El Husseiniya is a city in Egypt’s Sharqia Governorate, known as a local administrative and population center in the eastern Nile Delta region.
  • E. al-Harra
    al-Harra is a district near Medina in present-day Saudi Arabia, historically known as the site of a major early Islamic conflict between Umayyad forces and the city's inhabitants.
  • 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: al-Mahūza
Triple: [Madā’in, hasPart, al-Mahūza]
Generated description
al-Mahūza was a district within the ancient city complex of Madā’in, historically known as a significant urban quarter in the region of lower Mesopotamia.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: al-Mahūza
Target entity description: al-Mahūza was a district within the ancient city complex of Madā’in, historically known as a significant urban quarter in the region of lower Mesopotamia.
  • A. Al-Mahawil
    Al-Mahawil is a town in central Iraq located within the historically significant Babylon Governorate.
  • B. Al-Mughraqa
    Al-Mughraqa is a Palestinian town in the central Gaza Strip, situated south of Gaza City and characterized by its predominantly agricultural community.
  • C. Al-Muzahimiyah
    Al-Muzahimiyah is a town in central Saudi Arabia that serves as a growing satellite community west of Riyadh.
  • D. El Husseiniya
    El Husseiniya is a city in Egypt’s Sharqia Governorate, known as a local administrative and population center in the eastern Nile Delta region.
  • E. al-Harra
    al-Harra is a district near Medina in present-day Saudi Arabia, historically known as the site of a major early Islamic conflict between Umayyad forces and the city's inhabitants.
  • 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_69e24554497c819080b996e071de27c2 completed April 17, 2026, 2:36 p.m.
NER Named-entity recognition batch_69f17b6040048190a36fa759e06136ea completed April 29, 2026, 3:30 a.m.
NED1 Entity disambiguation (via context triple) batch_6a0b9822db848190b8498f7bc47bf7e2 completed May 18, 2026, 10:52 p.m.
NEDg Description generation batch_6a0b98e33b78819084ac449dd47cc778 completed May 18, 2026, 10:55 p.m.
NED2 Entity disambiguation (via description) batch_6a0b9996e05c8190ad2cb5704bb4c245 completed May 18, 2026, 10:58 p.m.
Created at: April 17, 2026, 3:27 p.m.