Triple

T8314034
Position Surface form Disambiguated ID Type / Status
Subject Muslim conquest of North Africa E194658 entity
Predicate hasOpponentCommander P1698 FINISHED
Object Dihya
Dihya, also known as al-Kahina, was a 7th-century Berber queen and military leader who led fierce resistance against the early Muslim expansion in North Africa.
 E725519 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: Dihya | Statement: [Muslim conquest of North Africa, hasOpponentCommander, Dihya]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Dihya
Context triple: [Muslim conquest of North Africa, hasOpponentCommander, Dihya]
  • A. Dijlah
    Dijlah is the Arabic name for the Tigris River, one of the major rivers of Western Asia flowing through Turkey, Syria, and Iraq.
  • B. Dairut
    Dairut is a city in Upper Egypt known as an important urban and agricultural center within the Asyut region along the Nile.
  • C. Dhiban
    Dhiban is an archaeological site and modern town in Jordan, historically significant as the ancient Moabite city of Dibon.
  • D. Kadiria
    Kadiria is a town and commune located within Bouira Province in northern Algeria.
  • E. Hasbaya
    Hasbaya is a historic town in southern Lebanon known for its strategic location near Mount Hermon and its traditional Druze and Christian 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: Dihya
Triple: [Muslim conquest of North Africa, hasOpponentCommander, Dihya]
Generated description
Dihya, also known as al-Kahina, was a 7th-century Berber queen and military leader who led fierce resistance against the early Muslim expansion in North Africa.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Dihya
Target entity description: Dihya, also known as al-Kahina, was a 7th-century Berber queen and military leader who led fierce resistance against the early Muslim expansion in North Africa.
  • A. Dijlah
    Dijlah is the Arabic name for the Tigris River, one of the major rivers of Western Asia flowing through Turkey, Syria, and Iraq.
  • B. Dairut
    Dairut is a city in Upper Egypt known as an important urban and agricultural center within the Asyut region along the Nile.
  • C. Dhiban
    Dhiban is an archaeological site and modern town in Jordan, historically significant as the ancient Moabite city of Dibon.
  • D. Kadiria
    Kadiria is a town and commune located within Bouira Province in northern Algeria.
  • E. Hasbaya
    Hasbaya is a historic town in southern Lebanon known for its strategic location near Mount Hermon and its traditional Druze and Christian 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_69ca82e6e2648190a31eaf6f4f757b2a completed March 30, 2026, 2:04 p.m.
NER Named-entity recognition batch_69cb7f52c5cc8190b5a95ee0aa4ddda5 completed March 31, 2026, 8:01 a.m.
NED1 Entity disambiguation (via context triple) batch_69cd957ac9788190b4253cca9b4b095d completed April 1, 2026, 10 p.m.
NEDg Description generation batch_69cdab5d649c819098a7643d5a0b7827 completed April 1, 2026, 11:33 p.m.
NED2 Entity disambiguation (via description) batch_69cdb2c2e2248190bf52466abaebfe29 completed April 2, 2026, 12:05 a.m.
Created at: March 30, 2026, 5:55 p.m.