Triple

T11093658
Position Surface form Disambiguated ID Type / Status
Subject Madi language E262317 entity
Predicate hasDialect P4251 FINISHED
Object Pakele
Pakele is a dialectal variety of the Madi language spoken by a subgroup of the Madi people in Central Africa.
E904343 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: Pakele | Statement: [Madi language, hasDialect, Pakele]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Pakele
Context triple: [Madi language, hasDialect, Pakele]
  • A. Polae
    Polae is a historical name referring to the ancient settlement known in later periods as Pola, a coastal city in the Istrian region.
  • B. Leale
    Leale is an Italian-origin surname borne by various individuals, including those in the arts and public life.
  • C. Petauke
    Petauke is a town in eastern Zambia that serves as an important commercial and transport hub for the surrounding rural region.
  • D. Kaula
    Kaula is a small, uninhabited rocky islet off the coast of Kauai in Hawaii, known for its steep cliffs, seabird colonies, and use as a U.S. Navy bombing range.
  • E. Lakalei
    Lakalei is an Austronesian language spoken by a small community in East Timor.
  • 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: Pakele
Triple: [Madi language, hasDialect, Pakele]
Generated description
Pakele is a dialectal variety of the Madi language spoken by a subgroup of the Madi people in Central Africa.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Pakele
Target entity description: Pakele is a dialectal variety of the Madi language spoken by a subgroup of the Madi people in Central Africa.
  • A. Polae
    Polae is a historical name referring to the ancient settlement known in later periods as Pola, a coastal city in the Istrian region.
  • B. Leale
    Leale is an Italian-origin surname borne by various individuals, including those in the arts and public life.
  • C. Petauke
    Petauke is a town in eastern Zambia that serves as an important commercial and transport hub for the surrounding rural region.
  • D. Kaula
    Kaula is a small, uninhabited rocky islet off the coast of Kauai in Hawaii, known for its steep cliffs, seabird colonies, and use as a U.S. Navy bombing range.
  • E. Lakalei
    Lakalei is an Austronesian language spoken by a small community in East Timor.
  • 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_69d6aa9a40d88190a373e2c7e48285db completed April 8, 2026, 7:20 p.m.
NER Named-entity recognition batch_69d799ed12d88190a4ad8c346d68f11f completed April 9, 2026, 12:22 p.m.
NED1 Entity disambiguation (via context triple) batch_69e3e7d3043c8190bdbe0ec51992db0c completed April 18, 2026, 8:21 p.m.
NEDg Description generation batch_69e3f2cbb4708190a328cff473104d14 completed April 18, 2026, 9:08 p.m.
NED2 Entity disambiguation (via description) batch_69e3f497a01881909d1dae70a02e5f97 completed April 18, 2026, 9:16 p.m.
Created at: April 8, 2026, 9:27 p.m.