Triple

T6419990
Position Surface form Disambiguated ID Type / Status
Subject Santhal E127920 entity
Predicate script P505 FINISHED
Object Ol Chiki E210851 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: Ol Chiki | Statement: [Santhal, script, Ol Chiki]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Ol Chiki
Context triple: [Santhal, script, Ol Chiki]
  • A. Ol Chiki script chosen
    Ol Chiki script is an alphabetic writing system specifically created in the 20th century for the Santhali language, used primarily by the Santal people of eastern India and neighboring regions.
  • B. Swaralipi
    Swaralipi is a significant literary and musical work by Bengali polymath Dwijendranath Tagore, reflecting his contributions to early modern Bengali culture and aesthetics.
  • C. Nepal Lipi
    Nepal Lipi is a historic Brahmic script traditionally used by the Newar people of Nepal to write the Nepal Bhasa language and several other regional languages.
  • D. Odia script
    Odia script is an abugida of the Brahmic family used primarily to write the Odia language and several other regional Indo-Aryan languages of eastern India.
  • E. Gondi script
    Gondi script is an abugida writing system used to represent the Gondi language spoken by the Gondi people of central India.
  • 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_69c0083815208190a9b299b8e0640218 completed March 22, 2026, 3:18 p.m.
NER Named-entity recognition batch_69c06902ddb48190bd5a8b5ecdf6c39e completed March 22, 2026, 10:11 p.m.
NED1 Entity disambiguation (via context triple) batch_69c640d5f6f88190963a1e59400c7aa0 completed March 27, 2026, 8:33 a.m.
Created at: March 22, 2026, 4:43 p.m.