Triple

T21942588
Position Surface form Disambiguated ID Type / Status
Subject Ta Oi E541858 entity
Predicate relatedEthnicGroup P1969 FINISHED
Object Co Tu 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: Co Tu | Statement: [Ta Oi, relatedEthnicGroup, Co Tu]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Co Tu
Context triple: [Ta Oi, relatedEthnicGroup, Co Tu]
  • A. Co Tu chosen
    The Co Tu are an indigenous ethnic minority group of Vietnam, traditionally living in the mountainous regions of central provinces such as Quang Tri and known for their distinct language, stilt houses, and rich communal rituals.
  • B. Queige
    Queige is a small commune in the Savoie department of southeastern France, situated in the Alpine Beaufortain region.
  • C. Co Le
    Co Le is a small town in Vietnam that serves as the administrative and economic center of Truc Ninh District in Nam Dinh Province.
  • D. Teok
    Teok is a town in the Jorhat district of Assam, India, known as a local commercial and transportation hub in the region.
  • E. Túr
    Túr is a river in Central Europe that flows through parts of Romania and Hungary before joining the Bodrog River.
  • 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_69e0c47e2e5c81909a7f74ce3de50911 completed April 16, 2026, 11:14 a.m.
NER Named-entity recognition batch_69f1242345dc8190aa6ddf61cf864e2d completed April 28, 2026, 9:18 p.m.
Created at: April 16, 2026, 7:56 p.m.