Triple

T12982612
Position Surface form Disambiguated ID Type / Status
Subject Wellamadama campus E321687 entity
Predicate near P350 FINISHED
Object city of Matara E323360 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: city of Matara | Statement: [Wellamadama campus, near, city of Matara]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: city of Matara
Context triple: [Wellamadama campus, near, city of Matara]
  • A. Matara chosen
    Matara is a major coastal city in southern Sri Lanka known for its historic fort, beaches, and role as a regional commercial and transport hub.
  • B. Matara District
    Matara District is an administrative district in southern Sri Lanka known for its coastal cities, historical sites, and agricultural hinterland.
  • C. Kotte
    Kotte is a historic Sri Lankan city that once served as the capital of a medieval kingdom and later gave its name to the modern administrative capital, Sri Jayawardenepura Kotte.
  • D. Matale
    Matale is a central Sri Lankan town known for its spice gardens, historical temples, and role in the island’s hill-country region.
  • E. Vavuniya town
    Vavuniya town is the principal urban and commercial hub of Sri Lanka’s Vavuniya District, serving as a key center for administration, trade, and transport in the island’s northern 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_69d8076479b8819090afce3591939cdf completed April 9, 2026, 8:09 p.m.
NER Named-entity recognition batch_69d97e5ca33481909a6cb06c636889f9 completed April 10, 2026, 10:49 p.m.
NED1 Entity disambiguation (via context triple) batch_69f6b8f4320881909d66eaa48f888fab completed May 3, 2026, 2:54 a.m.
Created at: April 9, 2026, 8:39 p.m.