Triple

T20357368
Position Surface form Disambiguated ID Type / Status
Subject Saku Parish E496684 entity
Predicate hasSettlement P1068 FINISHED
Object Kangru 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: Kangru | Statement: [Saku Parish, hasSettlement, Kangru]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Kangru
Context triple: [Saku Parish, hasSettlement, Kangru]
  • A. Kangru chosen
    Kangru is a small village located within Kiili Parish in northern Estonia.
  • B. Wallichia
    Wallichia is a genus of palms native to South and Southeast Asia, named in honor of the Danish botanist Nathaniel Wallich.
  • C. Kashi Kingdom
    Kashi Kingdom was an ancient Indian kingdom centered around the sacred city of Varanasi (Kashi), renowned as a major cultural and religious hub in early South Asian history.
  • D. Kangra kingdom
    Kangra kingdom was a historic Himalayan principality in present-day Himachal Pradesh, known for its strategic hill forts, rich cultural heritage, and distinctive Pahari art traditions.
  • E. Nag Champa
    Nag Champa is a popular aromatic blend, often used in incense and oils, known for its sweet, earthy, and floral fragrance associated with meditation and spiritual practices.
  • 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_69e0b4a3f7f48190b37f354574028ca6 completed April 16, 2026, 10:06 a.m.
NER Named-entity recognition batch_69e67854c0448190ab10363f8a218afb completed April 20, 2026, 7:02 p.m.
Created at: April 16, 2026, 11:25 a.m.