Triple

T22231074
Position Surface form Disambiguated ID Type / Status
Subject Coastal Line E549466 entity
Predicate connectsCity P4245 FINISHED
Object Matara 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: Matara | Statement: [Coastal Line, connectsCity, Matara]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Matara
Context triple: [Coastal Line, connectsCity, 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. Matara, Sri Lanka
    Matara, Sri Lanka is a major coastal city in the Southern Province known for its historic fort, beaches, and role as a regional commercial and cultural hub.
  • D. Unawatuna
    Unawatuna is a popular coastal town in southern Sri Lanka known for its palm-fringed beach, coral-rich bay, and laid-back tourist atmosphere.
  • E. Malabe
    Malabe is a rapidly developing suburb in the Colombo District of Sri Lanka, known for its IT parks, private universities, and growing residential communities.
  • 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_69e11e4102b881909cf47d3768e25c19 completed April 16, 2026, 5:37 p.m.
NER Named-entity recognition batch_69f12bf2a26c81908aaf614d7c75e219 completed April 28, 2026, 9:51 p.m.
Created at: April 16, 2026, 8:38 p.m.