Triple

T7166160
Position Surface form Disambiguated ID Type / Status
Subject Hyderabad Division E167072 entity
Predicate hasMajorLanguage P207 FINISHED
Object Urdu E6054 NE FINISHED

Named-entity recognition

Before disambiguation, gpt-5-mini classified whether the object phrase is a named entity — the step behind the object's NE type shown above.

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: Urdu | Statement: [Hyderabad Division, hasMajorLanguage, Urdu]

Disambiguation candidates (1 decision)

The exact options the model was shown at each disambiguation step, with the option it chose highlighted — the evidence behind this triple's disambiguated ids.

NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Urdu
Context triple: [Hyderabad Division, hasMajorLanguage, Urdu]
  • A. Urdu language chosen
    Urdu is a major South Asian language, written in a Perso-Arabic script and widely used in Pakistan and parts of India in literature, media, and everyday communication.
  • B. Sindhi
    Sindhi is an Indo-Aryan language spoken primarily in Pakistan and India, known for its rich literary tradition and distinct script variants.
  • C. Saraiki
    Saraiki is an Indo-Aryan language spoken primarily in central and southern Pakistan, especially in the southern Punjab region.
  • D. Balochi
    Balochi is an Iranian language spoken primarily by the Baloch people across Pakistan, Iran, and Afghanistan, with several dialects and a rich oral literary tradition.
  • E. Punjabi
    Punjabi refers to the ethnolinguistic group native to the Punjab region of South Asia, known for its distinct language, culture, and traditions shared across parts of India and Pakistan.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (3 batches)

Stage Batch ID Job type Status
creating batch_69c68888c10c819095e0383020225758 elicitation completed
NER batch_69c6e85a07388190a07054ef12870fa1 ner completed
NED1 batch_69c7b901cb608190acd25c22b38a1957 ned_source_triple completed
Created at: March 27, 2026, 2:48 p.m.