Triple

T2509345
Position Surface form Disambiguated ID Type / Status
Subject Hadza language E52662 entity
Predicate hasNeighboringLanguages P16383 FINISHED
Object Iraqw
Iraqw is a Cushitic language spoken primarily by the Iraqw people in northern Tanzania.
 E273031 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: Iraqw | Statement: [Hadza language, hasNeighboringLanguages, Iraqw]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Iraqw
Context triple: [Hadza language, hasNeighboringLanguages, Iraqw]
  • A. Warji
    Warji is a Chadic language spoken primarily in northern Nigeria by the Warji people.
  • B. Wilkasy
    Wilkasy is a village and popular lakeside tourist resort in northeastern Poland’s Warmian-Masurian Voivodeship, known for its marinas and access to the Masurian Lake District.
  • C. Gweru
    Gweru is a central Zimbabwean city that serves as the capital of the Midlands Province and an important commercial and transportation hub.
  • D. Hwaci
    Hwaci is the small American software company best known for creating and maintaining the SQLite relational database engine.
  • E. Kungara
    Kungara is an alternative name for the Fur language, a Nilo-Saharan language spoken primarily by the Fur people of western Sudan.
  • 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: Iraqw
Triple: [Hadza language, hasNeighboringLanguages, Iraqw]
Generated description
Iraqw is a Cushitic language spoken primarily by the Iraqw people in northern Tanzania.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Iraqw
Target entity description: Iraqw is a Cushitic language spoken primarily by the Iraqw people in northern Tanzania.
  • A. Warji
    Warji is a Chadic language spoken primarily in northern Nigeria by the Warji people.
  • B. Wilkasy
    Wilkasy is a village and popular lakeside tourist resort in northeastern Poland’s Warmian-Masurian Voivodeship, known for its marinas and access to the Masurian Lake District.
  • C. Gweru
    Gweru is a central Zimbabwean city that serves as the capital of the Midlands Province and an important commercial and transportation hub.
  • D. Hwaci
    Hwaci is the small American software company best known for creating and maintaining the SQLite relational database engine.
  • E. Kungara
    Kungara is an alternative name for the Fur language, a Nilo-Saharan language spoken primarily by the Fur people of western Sudan.
  • 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_69ab4958e76481908a235377dd921c9e completed March 6, 2026, 9:38 p.m.
NER Named-entity recognition batch_69abd1ed94a08190a172a426c2123f36 completed March 7, 2026, 7:21 a.m.
NED1 Entity disambiguation (via context triple) batch_69af1faa33148190a3ad6ece7432b81f completed March 9, 2026, 7:29 p.m.
NEDg Description generation batch_69af20aafd008190ad9fee7c154f8597 completed March 9, 2026, 7:34 p.m.
NED2 Entity disambiguation (via description) batch_69af2193102c81908f5fe1c899cc1a85 completed March 9, 2026, 7:37 p.m.
Created at: March 6, 2026, 9:46 p.m.