Triple

T4216209
Position Surface form Disambiguated ID Type / Status
Subject Kandy E94221 entity
Predicate languageMajority P237 FINISHED
Object Sinhala E10172 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: Sinhala | Statement: [Kandy, languageMajority, Sinhala]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Sinhala
Context triple: [Kandy, languageMajority, Sinhala]
  • A. Sinhala chosen
    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.
  • B. Sinhalese
    The Sinhalese are the largest ethnic group in Sri Lanka, predominantly Buddhist and historically associated with the island’s Sinhala language and culture.
  • 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. Sri Lankan Malay
    Sri Lankan Malay is an Austronesian language spoken by the Malay minority in Sri Lanka, reflecting a blend of Malay, Sinhala, and Tamil influences.
  • 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_69b3451997e08190851db4a9a588837d completed March 12, 2026, 10:58 p.m.
NER Named-entity recognition batch_69b34bea284081909beaded9873f0852 completed March 12, 2026, 11:27 p.m.
NED1 Entity disambiguation (via context triple) batch_69b5a852e0448190bc488087e92a94d4 completed March 14, 2026, 6:26 p.m.
Created at: March 12, 2026, 11:04 p.m.