Triple

T13493830
Position Surface form Disambiguated ID Type / Status
Subject Kandyan Kingdom E320707 entity
Predicate capital P234 FINISHED
Object Kandy E94221 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: Kandy | Statement: [Kandyan Kingdom, capital, Kandy]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Kandy
Context triple: [Kandyan Kingdom, capital, Kandy]
  • A. Kandy chosen
    Kandy is a historic city in central Sri Lanka renowned for its cultural heritage, including the Temple of the Tooth and its role as a former royal stronghold.
  • B. Kegalle
    Kegalle is a major town in central Sri Lanka known for its rubber plantations and proximity to the Pinnawala Elephant Orphanage.
  • C. Dambulla
    Dambulla is a historic town in Sri Lanka best known for its UNESCO-listed cave temple complex featuring ancient Buddhist murals and statues.
  • D. Badulla
    Badulla is a major town in Sri Lanka’s central highlands, known as the capital of Uva Province and a regional hub surrounded by tea plantations and scenic mountain landscapes.
  • E. Gampola
    Gampola is a historic town in Sri Lanka known for its former status as a medieval capital and its scenic hill-country setting.
  • 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_69d807629d6c8190998f1b9bb12d2ed0 completed April 9, 2026, 8:09 p.m.
NER Named-entity recognition batch_69dbaf4da2c88190a867b53529d39545 completed April 12, 2026, 2:42 p.m.
NED1 Entity disambiguation (via context triple) batch_69fbc3138cc48190acb28a18ac9bb3eb completed May 6, 2026, 10:39 p.m.
Created at: April 9, 2026, 9:43 p.m.