Triple

T441148
Position Surface form Disambiguated ID Type / Status
Subject Zulu E10115 entity
Predicate closelyRelatedTo P37 FINISHED
Object Swati E58238 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: Swati | Statement: [Zulu, closelyRelatedTo, Swati]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Swati
Context triple: [Zulu, closelyRelatedTo, Swati]
  • A. Swati chosen
    Swati is a Bantu language of the Nguni group, primarily spoken in Eswatini and parts of South Africa.
  • B. Indravati
    Indravati is a significant river in central India that flows through states like Chhattisgarh and Odisha before joining the Godavari River.
  • C. Narmada
    Narmada is a major river in central India, revered in Hinduism and known for flowing westward into the Arabian Sea through a deep rift valley.
  • D. Saraswati
    Saraswati is the Hindu goddess of knowledge, wisdom, music, and the arts, revered as the divine embodiment of learning and creative inspiration.
  • E. Yamuna
    Yamuna is a major sacred river of northern India, flowing through cities like Delhi and Agra and serving as a key tributary of the Ganges.
  • 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_69a2e8465ef481909655c681b01e2986 completed Feb. 28, 2026, 1:06 p.m.
NER Named-entity recognition batch_69a2ef2af84881909635ebbbb3465b1b completed Feb. 28, 2026, 1:35 p.m.
NED1 Entity disambiguation (via context triple) batch_69a46c5a949081908e05f0b61795004f completed March 1, 2026, 4:42 p.m.
Created at: Feb. 28, 2026, 1:11 p.m.