Triple

T21939136
Position Surface form Disambiguated ID Type / Status
Subject Loona E541769 entity
Predicate script P505 FINISHED
Object Gurmukhi NE NERFINISHED

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: Gurmukhi | Statement: [Loona, script, Gurmukhi]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Gurmukhi
Context triple: [Loona, script, Gurmukhi]
  • A. Gurmukhi chosen
    Gurmukhi is an Indic writing system primarily used for the Punjabi language and for recording Sikh religious scriptures.
  • B. Multani script
    Multani script is a historical Brahmic writing system once used primarily for the Multani language and mercantile records in the Multan region of the Indian subcontinent.
  • C. Gaddi Dogri
    Gaddi Dogri is an Indo-Aryan language variety spoken primarily by the Gaddi community in the northern Indian Himalayas.
  • D. Gujarati script
    The Gujarati script is an abugida used primarily to write the Gujarati language and related Indo-Aryan languages, derived from the Devanagari script and characterized by the absence of the horizontal headline.
  • E. Shahmukhi script
    Shahmukhi script is a Perso-Arabic–based writing system primarily used for writing the Punjabi language in Pakistan.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 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_69e0c47e2e5c81909a7f74ce3de50911 completed April 16, 2026, 11:14 a.m.
NER Named-entity recognition batch_69f1241f582c81909a244419cec38b19 completed April 28, 2026, 9:18 p.m.
Created at: April 16, 2026, 7:55 p.m.