Triple

T18935402
Position Surface form Disambiguated ID Type / Status
Subject Matale District E463230 entity
Predicate contains P35 FINISHED
Object Matale city 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: Matale city | Statement: [Matale District, contains, Matale city]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Matale city
Context triple: [Matale District, contains, Matale city]
  • A. Matale chosen
    Matale is a central Sri Lankan town known for its spice gardens, historical temples, and role in the island’s hill-country region.
  • B. Matale District
    Matale District is an administrative district in central Sri Lanka known for its spice plantations, historical sites, and mountainous landscapes.
  • C. Karuma town
    Karuma town is a settlement in northern Uganda situated near the Karuma Falls on the Nile River, known primarily for its proximity to the Karuma Hydropower Station.
  • D. Ciudad Ojeda
    Ciudad Ojeda is an oil-industry city in northwestern Venezuela, located on the eastern shore of Lake Maracaibo in Zulia state.
  • E. City of Coyhaique
    The City of Coyhaique is the principal urban center and regional capital of Chile’s Aysén Region, known for its role as a gateway to Patagonia’s rugged landscapes and outdoor tourism.
  • 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_69d8dcfec90481909e926be9767e5779 completed April 10, 2026, 11:20 a.m.
NER Named-entity recognition batch_69e5d3e6a8208190973669cae439a91e completed April 20, 2026, 7:21 a.m.
Created at: April 10, 2026, 11:59 a.m.