Triple

T13951888
Position Surface form Disambiguated ID Type / Status
Subject Badulla E335546 entity
Predicate capitalOf P204 FINISHED
Object Uva Province E466101 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: Uva Province | Statement: [Badulla, capitalOf, Uva Province]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Uva Province
Context triple: [Badulla, capitalOf, Uva Province]
  • A. Uva Province chosen
    Uva Province is one of the nine provinces of Sri Lanka, known for its mountainous terrain, tea plantations, and scenic waterfalls.
  • B. Isabel Province
    Isabel Province is a largely rural island province in the Solomon Islands, known for its mountainous terrain, traditional villages, and rich marine and forest biodiversity.
  • C. Peravia Province
    Peravia Province is a coastal administrative region in the southern Dominican Republic known for its capital city Baní, agricultural production, and salt flats.
  • D. Almeidas Province
    Almeidas Province is an administrative subdivision of the Cundinamarca Department in central Colombia, comprising several municipalities in the Andean highlands.
  • E. La Mar Province
    La Mar Province is an administrative province located in the Ayacucho Region of south-central Peru, known for its Andean geography and predominantly rural communities.
  • 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_69d81c6081b88190b53e317c3370c8fe completed April 9, 2026, 9:38 p.m.
NER Named-entity recognition batch_69de2e146720819085d0f5eae558b7a4 completed April 14, 2026, 12:07 p.m.
NED1 Entity disambiguation (via context triple) batch_69fbac8c06ec8190a6dfceab55da5b30 completed May 6, 2026, 9:03 p.m.
Created at: April 9, 2026, 10:17 p.m.