Triple

T9352371
Position Surface form Disambiguated ID Type / Status
Subject Bura-Pabir E225048 entity
Predicate hasNeighboringLanguage P16383 FINISHED
Object Marghi
Marghi is a Chadic language spoken by the Marghi people in northeastern Nigeria.
 E793221 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: Marghi | Statement: [Bura-Pabir, hasNeighboringLanguage, Marghi]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Marghi
Context triple: [Bura-Pabir, hasNeighboringLanguage, Marghi]
  • A. Masarra
    Masarra is a passenger station on Cairo Metro’s Line 2 serving commuters in the Cairo metropolitan area.
  • B. Molazzana
    Molazzana is a small municipality in Tuscany, central Italy, known for its scenic location in the Garfagnana area of the Apennine mountains.
  • C. Ghomari
    Ghomari is an alternative name for the Ghomara language, a Northern Berber language spoken by the Ghomara people in northern Morocco.
  • D. Maraig
    Maraig is a small coastal settlement in the Outer Hebrides of Scotland, situated on the shores of Loch Seaforth on the Isle of Harris.
  • E. Jabriya
    Jabriya is a residential suburb in Kuwait known for its mix of apartment buildings, schools, and local shops within the Hawalli Governorate.
  • 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: Marghi
Triple: [Bura-Pabir, hasNeighboringLanguage, Marghi]
Generated description
Marghi is a Chadic language spoken by the Marghi people in northeastern Nigeria.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Marghi
Target entity description: Marghi is a Chadic language spoken by the Marghi people in northeastern Nigeria.
  • A. Masarra
    Masarra is a passenger station on Cairo Metro’s Line 2 serving commuters in the Cairo metropolitan area.
  • B. Molazzana
    Molazzana is a small municipality in Tuscany, central Italy, known for its scenic location in the Garfagnana area of the Apennine mountains.
  • C. Ghomari
    Ghomari is an alternative name for the Ghomara language, a Northern Berber language spoken by the Ghomara people in northern Morocco.
  • D. Maraig
    Maraig is a small coastal settlement in the Outer Hebrides of Scotland, situated on the shores of Loch Seaforth on the Isle of Harris.
  • E. Jabriya
    Jabriya is a residential suburb in Kuwait known for its mix of apartment buildings, schools, and local shops within the Hawalli Governorate.
  • 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_69ca842abfd48190949d71c3b86eeba8 completed March 30, 2026, 2:09 p.m.
NER Named-entity recognition batch_69cd4f93a9848190ad2ae24f2aa607d2 completed April 1, 2026, 5:02 p.m.
NED1 Entity disambiguation (via context triple) batch_69d0e44f0a7881908b53a97715f4c6da completed April 4, 2026, 10:13 a.m.
NEDg Description generation batch_69d0e5752a38819089b23ac52f0a6a39 completed April 4, 2026, 10:18 a.m.
NED2 Entity disambiguation (via description) batch_69d0e64cb4dc81908cef7d729d9cfb4d completed April 4, 2026, 10:22 a.m.
Created at: March 30, 2026, 7:41 p.m.