Triple

T8301974
Position Surface form Disambiguated ID Type / Status
Subject Bengali Wikinews E194368 entity
Predicate sisterProjectOf P19167 FINISHED
Object Bengali Wiktionary E37903 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: Bengali Wiktionary | Statement: [Bengali Wikinews, sisterProjectOf, Bengali Wiktionary]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Bengali Wiktionary
Context triple: [Bengali Wikinews, sisterProjectOf, Bengali Wiktionary]
  • A. Bengali
    Bengali is an Indo-Aryan language spoken primarily in the Bengal region of South Asia and serving as the official and most widely used language of Bangladesh and the Indian state of West Bengal.
  • B. Bengali Wikinews
    Bengali Wikinews is the Bengali-language edition of the Wikinews project, providing collaboratively written, free-content news articles for Bengali-speaking audiences.
  • C. Wiktionary chosen
    Wiktionary is a collaboratively edited, multilingual online dictionary and lexical resource.
  • D. Bangladeshi
    Bangladeshi refers to a person or attribute associated with Bangladesh, particularly its people, nationality, or cultural heritage.
  • E. Ei Thesaurus
    Ei Thesaurus is a controlled vocabulary and indexing tool used to standardize subject terms for engineering and technical literature in the Ei Compendex database.
  • 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_69ca82e50ebc81909aa7b260c76bd757 completed March 30, 2026, 2:04 p.m.
NER Named-entity recognition batch_69cb7e891030819097f4a26992a8b469 completed March 31, 2026, 7:58 a.m.
NED1 Entity disambiguation (via context triple) batch_69cd68c2a14c81908388ecdd22315390 completed April 1, 2026, 6:49 p.m.
Created at: March 30, 2026, 5:53 p.m.