Triple

T23506048
Position Surface form Disambiguated ID Type / Status
Subject Tagin language E572283 entity
Predicate languageGroup P3349 FINISHED
Object Tani NE NERFINISHED

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: Tani | Statement: [Tagin language, languageGroup, Tani]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Tani
Context triple: [Tagin language, languageGroup, Tani]
  • A. Tani chosen
    Tani is a group of closely related Tibeto-Burman languages spoken primarily in the northeastern Indian states of Arunachal Pradesh and Assam.
  • B. Tani
    Tani is a Pashtun tribal group primarily associated with Afghanistan’s Khost region.
  • C. Tani Tateki
    Tani Tateki was a Japanese samurai and military commander of the Meiji era who played a key role in government forces during the Satsuma Rebellion.
  • D. Tayan
    Tayan is the endonym used by the Atayal, an Indigenous Austronesian people of Taiwan, to refer to themselves.
  • E. Yulu
    Yulu is a Central Sudanic language spoken by the Yulu people primarily in parts of South Sudan and the Central African Republic.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 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_69e245b5e4208190bac8a6509867e394 completed April 17, 2026, 2:37 p.m.
NER Named-entity recognition batch_69f1a9009ca081908c4cffb8c32293ec completed April 29, 2026, 6:45 a.m.
Created at: April 17, 2026, 6:07 p.m.