Triple

T7098036
Position Surface form Disambiguated ID Type / Status
Subject Hambantota E165380 entity
Predicate nearbyCity P350 FINISHED
Object 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: Matara | Statement: [Hambantota, nearbyCity, Matara]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Matara
Context triple: [Hambantota, nearbyCity, 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. 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.
  • D. Vilankulo
    Vilankulo is a coastal town in southern Mozambique known as the main gateway to the nearby Bazaruto Archipelago and its popular beach and marine tourism.
  • E. Ampara
    Ampara is a major town in Sri Lanka known as an agricultural and administrative center in the island’s Eastern Province.
  • 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_69c6887fcddc8190a5d58908f6dee590 completed March 27, 2026, 1:39 p.m.
NER Named-entity recognition batch_69c6e5561dd08190be6b784754a0c1bc completed March 27, 2026, 8:15 p.m.
NED1 Entity disambiguation (via context triple) batch_69c79ca2be7c8190b5a8c6f2c64a0d8d completed March 28, 2026, 9:17 a.m.
Created at: March 27, 2026, 2:42 p.m.