Triple

T5993214
Position Surface form Disambiguated ID Type / Status
Subject Ancient City of Sigiriya E133401 entity
Predicate locatedIn P40 FINISHED
Object Matale District E463230 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: Matale District | Statement: [Ancient City of Sigiriya, locatedIn, Matale District]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Matale District
Context triple: [Ancient City of Sigiriya, locatedIn, Matale District]
  • A. Matale District chosen
    Matale District is an administrative district in central Sri Lanka known for its spice plantations, historical sites, and mountainous landscapes.
  • B. Guarda District
    Guarda District is an inland administrative region in northeastern Portugal known for its mountainous landscapes, historic fortified towns, and proximity to the Douro wine region.
  • C. Bealanana District
    Bealanana District is an administrative district in northern Madagascar that encompasses the area around Maromokotro, the country’s highest peak.
  • D. Buvuma District
    Buvuma District is an administrative district in Uganda that encompasses Buvuma Island and surrounding islands in Lake Victoria.
  • E. Urambo District
    Urambo District is an administrative district in western Tanzania known for its rural communities and tobacco farming, located within the Tabora Region.
  • 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_69c00870ddbc81909880fa3864f4f38d completed March 22, 2026, 3:19 p.m.
NER Named-entity recognition batch_69c04e9189908190abc9c742b38dfabc completed March 22, 2026, 8:18 p.m.
NED1 Entity disambiguation (via context triple) batch_69c108685f788190aa3f84e56837b195 completed March 23, 2026, 9:31 a.m.
Created at: March 22, 2026, 4:05 p.m.