Triple

T18626801
Position Surface form Disambiguated ID Type / Status
Subject Huave language E455304 entity
Predicate hasAlternativeName P39 FINISHED
Object Wabe
Wabe is an alternative name for the Huave language, an indigenous language spoken by the Huave people of Oaxaca, Mexico.
E1335004 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: Wabe | Statement: [Huave language, hasAlternativeName, Wabe]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Wabe
Context triple: [Huave language, hasAlternativeName, Wabe]
  • A. Waabs
    Waabs is a small coastal municipality in northern Germany’s Schleswig-Holstein region, known for its Baltic Sea beaches and rural landscape.
  • B. Wabho
    Wabho is a town located in the Galguduud region of central Somalia.
  • C. Wanze
    Wanze is a municipality in eastern Belgium situated along the Meuse River in the Walloon Region.
  • D. Wybe
    Wybe is the given first name of the renowned Dutch computer scientist Edsger W. Dijkstra.
  • E. Wahpe Kute
    Wahpe Kute is one of the historical bands of the Eastern Dakota (Sioux) people, traditionally living in parts of what are now Minnesota and surrounding regions.
  • 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: Wabe
Triple: [Huave language, hasAlternativeName, Wabe]
Generated description
Wabe is an alternative name for the Huave language, an indigenous language spoken by the Huave people of Oaxaca, Mexico.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Wabe
Target entity description: Wabe is an alternative name for the Huave language, an indigenous language spoken by the Huave people of Oaxaca, Mexico.
  • A. Waabs
    Waabs is a small coastal municipality in northern Germany’s Schleswig-Holstein region, known for its Baltic Sea beaches and rural landscape.
  • B. Wabho
    Wabho is a town located in the Galguduud region of central Somalia.
  • C. Wanze
    Wanze is a municipality in eastern Belgium situated along the Meuse River in the Walloon Region.
  • D. Wybe
    Wybe is the given first name of the renowned Dutch computer scientist Edsger W. Dijkstra.
  • E. Wahpe Kute
    Wahpe Kute is one of the historical bands of the Eastern Dakota (Sioux) people, traditionally living in parts of what are now Minnesota and surrounding regions.
  • 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_69d8d38cc7948190a55ea64e5638994e completed April 10, 2026, 10:40 a.m.
NER Named-entity recognition batch_69e54f0581f0819083c1aba9fb85f6a7 completed April 19, 2026, 9:54 p.m.
NED1 Entity disambiguation (via context triple) batch_6a050d7a6f048190832624811bb8e2ea completed May 13, 2026, 11:47 p.m.
NEDg Description generation batch_6a05102a5ba481908d94f38540ed9fc8 completed May 13, 2026, 11:58 p.m.
NED2 Entity disambiguation (via description) batch_6a0510ae8a208190abd0209218dbe2f5 completed May 14, 2026, midnight
Created at: April 10, 2026, 11:46 a.m.