Triple

T16368813
Position Surface form Disambiguated ID Type / Status
Subject River God E397508 entity
Predicate narrator P2181 FINISHED
Object Taita E893968 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: Taita | Statement: [River God, narrator, Taita]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Taita
Context triple: [River God, narrator, Taita]
  • A. Taita
    Taita is a residential suburb in the Hutt Valley region near Wellington, New Zealand.
  • B. Taita chosen
    The Taita are a Bantu-speaking ethnic group of southeastern Kenya, primarily inhabiting the Taita Hills and known for mixed farming and rich highland cultural traditions.
  • C. Wilis
    Wilis are vengeful female spirits of betrayed brides in the ballet "Giselle," who rise from their graves at night to force men to dance to their deaths.
  • D. Tibás
    Tibás is an urban canton in Costa Rica known for being part of the Greater San José metropolitan area and home to the popular football club Deportivo Saprissa.
  • E. Seppa
    Seppa is a town in the East Kameng district of Arunachal Pradesh in northeastern India, serving as an administrative and cultural center in the Himalayan foothills.
  • 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_69d87f2778dc8190aa95c7572db127e6 completed April 10, 2026, 4:40 a.m.
NER Named-entity recognition batch_69e2ff4021e88190ad093bab74cf82a4 completed April 18, 2026, 3:49 a.m.
NED1 Entity disambiguation (via context triple) batch_6a0035600420819087c909a615d205a2 completed May 10, 2026, 7:36 a.m.
Created at: April 10, 2026, 5:08 a.m.