Triple

T3055443
Position Surface form Disambiguated ID Type / Status
Subject Dinka language E60468 entity
Predicate hasDialect P4251 FINISHED
Object Agar Dinka
Agar Dinka is a dialect of the Dinka language spoken by the Agar subgroup of the Dinka people in South Sudan.
 E323725 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: Agar Dinka | Statement: [Dinka language, hasDialect, Agar Dinka]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Agar Dinka
Context triple: [Dinka language, hasDialect, Agar Dinka]
  • A. Ranna
    Ranna was a prominent 10th-century Kannada poet, celebrated as one of the “three gems” of early Kannada literature for his influential epic and courtly works.
  • B. Dausa
    Dausa is a town and district headquarters in the Indian state of Rajasthan, known for its historical forts, stepwells, and proximity to Jaipur.
  • C. Bahir
    Bahir is an early and influential mystical work of Jewish Kabbalah that explores esoteric interpretations of the Hebrew Bible and divine emanations.
  • D. Darsa
    Darsa is a small, sparsely inhabited island in the Indian Ocean that forms part of Yemen’s remote Socotra archipelago, known for its isolation and rich marine life.
  • E. Terevaka
    Terevaka is a large extinct volcanic peak that forms the highest and youngest of the three main volcanoes making up Easter Island.
  • 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: Agar Dinka
Triple: [Dinka language, hasDialect, Agar Dinka]
Generated description
Agar Dinka is a dialect of the Dinka language spoken by the Agar subgroup of the Dinka people in South Sudan.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Agar Dinka
Target entity description: Agar Dinka is a dialect of the Dinka language spoken by the Agar subgroup of the Dinka people in South Sudan.
  • A. Ranna
    Ranna was a prominent 10th-century Kannada poet, celebrated as one of the “three gems” of early Kannada literature for his influential epic and courtly works.
  • B. Dausa
    Dausa is a town and district headquarters in the Indian state of Rajasthan, known for its historical forts, stepwells, and proximity to Jaipur.
  • C. Bahir
    Bahir is an early and influential mystical work of Jewish Kabbalah that explores esoteric interpretations of the Hebrew Bible and divine emanations.
  • D. Darsa
    Darsa is a small, sparsely inhabited island in the Indian Ocean that forms part of Yemen’s remote Socotra archipelago, known for its isolation and rich marine life.
  • E. Terevaka
    Terevaka is a large extinct volcanic peak that forms the highest and youngest of the three main volcanoes making up Easter Island.
  • 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_69ad8578137c81908259dcb27c7d6d7c completed March 8, 2026, 2:19 p.m.
NER Named-entity recognition batch_69ad9bf6b9948190bc957bfd1579c471 completed March 8, 2026, 3:55 p.m.
NED1 Entity disambiguation (via context triple) batch_69b1ef03425c8190a44486ab563c210f completed March 11, 2026, 10:38 p.m.
NEDg Description generation batch_69b1f2d6e2008190adad44758e2d4766 completed March 11, 2026, 10:55 p.m.
NED2 Entity disambiguation (via description) batch_69b1f34005c88190817c40dc30f99f14 completed March 11, 2026, 10:57 p.m.
Created at: March 8, 2026, 3:02 p.m.