Triple

T8495923
Position Surface form Disambiguated ID Type / Status
Subject Colombo Tamil E201097 entity
Predicate differsFrom P278 FINISHED
Object Jaffna Tamil E40200 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: Jaffna Tamil | Statement: [Colombo Tamil, differsFrom, Jaffna Tamil]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Jaffna Tamil
Context triple: [Colombo Tamil, differsFrom, Jaffna Tamil]
  • A. Jaffna Tamil chosen
    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.
  • B. 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.
  • C. Sinhalese
    The Sinhalese are the largest ethnic group in Sri Lanka, predominantly Buddhist and historically associated with the island’s Sinhala language and culture.
  • D. 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.
  • E. Tamil
    Tamil is a classical Dravidian language spoken predominantly in the Indian state of Tamil Nadu and in parts of Sri Lanka, with a rich literary tradition spanning over two millennia.
  • 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_69ca831ee390819095fae73400bbfafc completed March 30, 2026, 2:05 p.m.
NER Named-entity recognition batch_69cbe57dbe488190af5f06faf862cd5d completed March 31, 2026, 3:17 p.m.
NED1 Entity disambiguation (via context triple) batch_69ce88d3e2808190856ee01cc20fbaec completed April 2, 2026, 3:18 p.m.
Created at: March 30, 2026, 6:13 p.m.