Triple

T11166924
Position Surface form Disambiguated ID Type / Status
Subject Yipunu E264182 entity
Predicate macrolanguage P5218 FINISHED
Object Punu languages E626647 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: Punu languages | Statement: [Yipunu, macrolanguage, Punu languages]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Punu languages
Context triple: [Yipunu, macrolanguage, Punu languages]
  • A. Punu languages chosen
    Punu languages are a subgroup of Bantu languages spoken primarily by the Punu people of Gabon and neighboring regions, known for their close linguistic and cultural ties to other Western Bantu groups.
  • B. Pame languages
    The Pame languages are a small group of closely related Oto-Manguean indigenous languages spoken by the Pame people in central Mexico.
  • C. Puruborá languages
    The Puruborá languages are a small, poorly documented branch of the Tupian language family once spoken by the Puruborá people of the Brazilian Amazon.
  • D. Pomoan languages
    The Pomoan languages are a group of closely related Indigenous languages traditionally spoken by the Pomo peoples of northern California.
  • E. Tebu languages
    The Tebu languages are a group of closely related Saharan languages spoken primarily by the Tebu people across parts of Chad, Niger, and Libya.
  • 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_69d6aa9dafac8190bd90d2c74f661aa7 completed April 8, 2026, 7:21 p.m.
NER Named-entity recognition batch_69d7e88843cc81909e503f0921c6d297 completed April 9, 2026, 5:57 p.m.
NED1 Entity disambiguation (via context triple) batch_69e4cc0f84008190b5306323aff4a300 completed April 19, 2026, 12:35 p.m.
Created at: April 8, 2026, 9:29 p.m.