Triple

T11515954
Position Surface form Disambiguated ID Type / Status
Subject Hadza language E273030 entity
Predicate hasAlternativeName P39 FINISHED
Object Hatsa E273030 NE FINISHED

How this triple was built (2 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: Hatsa | Statement: [Hadza language, hasAlternativeName, Hatsa]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Hatsa
Context triple: [Hadza language, hasAlternativeName, Hatsa]
  • A. Hatsa chosen
    Hatsa is an alternative name for the Hadza language, a highly distinctive click language spoken by the Hadza people of north-central Tanzania.
  • B. Tewa
    Tewa is a group of closely related Tanoan languages spoken by several Pueblo communities in northern New Mexico and parts of Arizona, central to their cultural and ceremonial life.
  • C. Rabha
    Rabha are an indigenous ethnic group of Northeast India, primarily inhabiting Assam and Meghalaya, known for their distinct Tibeto-Burman language, agrarian lifestyle, and rich folk traditions.
  • D. Moluche
    Moluche is a historical indigenous people of south-central Chile whose language is part of the broader Araucanian (Mapuche) language family.
  • E. Xibe
    The Xibe are a Tungusic-speaking ethnic minority in China, culturally related to the Manchu and known for their historical role as frontier garrisons in regions such as Xinjiang.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (3 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_69d6aae2c3748190bed2ea50dfb160dc completed April 8, 2026, 7:22 p.m.
NER Named-entity recognition batch_69d87fcc72a48190b81acedfcc8685d3 completed April 10, 2026, 4:42 a.m.
NED1 Entity disambiguation (via context triple) batch_69e625143a608190a1119b30c08df0fd completed April 20, 2026, 1:07 p.m.
Created at: April 8, 2026, 9:36 p.m.