Triple

T447924
Position Surface form Disambiguated ID Type / Status
Subject Sikhism E7061 entity
Predicate languageOfScripture P1187 FINISHED
Object Gurmukhi E12238 NE FINISHED

How this triple was built (3 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: [Sikhism, languageOfScripture, Gurmukhi]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Gurmukhi
Context triple: [Sikhism, languageOfScripture, Gurmukhi]
  • A. Gurmukhi chosen
    Gurmukhi is an Indic writing system primarily used for the Punjabi language and for recording Sikh religious scriptures.
  • B. 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.
  • C. Shahmukhi script
    Shahmukhi script is a Perso-Arabic–based writing system primarily used for writing the Punjabi language in Pakistan.
  • D. Dogri
    Dogri is an Indo-Aryan language spoken primarily in the Jammu region of India and surrounding areas, recognized as one of the official languages of India.
  • E. Devanagari script
    Devanagari script is an abugida writing system used for several major South Asian languages, including Hindi, Marathi, Nepali, and Sanskrit.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: languageOfScripture
Context triple: [Sikhism, languageOfScripture, Gurmukhi]
  • A. hasLanguageOfScripture chosen
    Indicates that an entity’s scriptural or sacred texts are written or expressed in a specified language.
  • B. inScripture
    Indicates that something is mentioned, described, or referenced within a scriptural or sacred text.
  • C. scriptureType
    Indicates the classification or category of a scripture in relation to its type or genre.
  • D. scripturalCorpus
    Indicates that one entity is a body of scriptural or sacred texts associated with, or serving as the canonical writings for, another entity.
  • E. hasScripture
    Indicates that one entity possesses, is associated with, or is defined by a particular scripture or set of scriptural texts.
  • F. None of above.

Provenance (4 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_69a2e7e4676c81909ea0dbdecac0687c completed Feb. 28, 2026, 1:04 p.m.
NER Named-entity recognition batch_69a2ef6429e881908aa758da64299a16 completed Feb. 28, 2026, 1:36 p.m.
NED1 Entity disambiguation (via context triple) batch_69a442a899d08190a0e3f04bffd4aca3 completed March 1, 2026, 1:44 p.m.
PD Predicate disambiguation batch_69a2ede1a1108190a4a06b3416ae6156 completed Feb. 28, 2026, 1:30 p.m.
Created at: Feb. 28, 2026, 1:12 p.m.