Triple

T1132697
Position Surface form Disambiguated ID Type / Status
Subject Sri Lanka E23066 entity
Predicate ethnicGroup P194 FINISHED
Object Sinhalese E128567 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: Sinhalese | Statement: [Sri Lanka, ethnicGroup, Sinhalese]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Sinhalese
Context triple: [Sri Lanka, ethnicGroup, Sinhalese]
  • A. Sinhalese chosen
    The Sinhalese are the largest ethnic group in Sri Lanka, predominantly Buddhist and historically associated with the island’s Sinhala language and culture.
  • B. Sinhala
    Sinhala is an Indo-Aryan language primarily spoken by the Sinhalese people of Sri Lanka and used as one of the country’s official languages.
  • C. Jaffna Tamil
    Jaffna Tamil is a distinct regional variety of the Tamil language spoken primarily in and around Jaffna in northern Sri Lanka, known for its conservative linguistic features and unique phonology and vocabulary.
  • D. Sinhala script
    The Sinhala script is an abugida writing system used primarily in Sri Lanka to write the Sinhala language and, to a lesser extent, Pali and Sanskrit.
  • E. Pali
    Pali is an ancient Middle Indo-Aryan liturgical language most notably used in the scriptures of Theravada Buddhism and influential across much of Southeast Asia.
  • 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_69a493ec75988190b63a11bafaec29b4 completed March 1, 2026, 7:30 p.m.
NER Named-entity recognition batch_69a4bbfcdf848190a2917d796ca84b74 completed March 1, 2026, 10:21 p.m.
NED1 Entity disambiguation (via context triple) batch_69ac667454848190acedaaa3ce7edb84 completed March 7, 2026, 5:55 p.m.
Created at: March 1, 2026, 7:44 p.m.