Triple

T2233562
Position Surface form Disambiguated ID Type / Status
Subject Maban languages E49225 entity
Predicate haveBorrowingsFrom P18996 FINISHED
Object Arabic E1330 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: Arabic | Statement: [Maban languages, haveBorrowingsFrom, Arabic]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Arabic
Context triple: [Maban languages, haveBorrowingsFrom, Arabic]
  • A. Arabic chosen
    Arabic is a Semitic language widely spoken across the Arab world and used as a liturgical language in Islam.
  • B. Hijazi Arabic
    Hijazi Arabic is a major regional variety of Arabic spoken primarily in western Saudi Arabia, especially in the Hijaz region including cities like Mecca, Medina, and Jeddah.
  • C. Badawi Najdi Arabic
    Badawi Najdi Arabic is a Bedouin variety of the Najdi Arabic dialect spoken primarily by nomadic and tribal communities in central Arabia.
  • D. Hassaniya Arabic
    Hassaniya Arabic is a variety of Arabic spoken primarily in Mauritania and parts of neighboring West African and Saharan countries, known for its Bedouin roots and distinctive phonology and vocabulary.
  • E. Egyptian Arabic
    Egyptian Arabic is the most widely understood modern Arabic dialect, centered in Egypt and heavily influenced by the speech and media of Cairo.
  • 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: haveBorrowingsFrom
Context triple: [Maban languages, haveBorrowingsFrom, Arabic]
  • A. hasBorrowingsFrom chosen
    Indicates that one entity has taken, adopted, or derived elements (such as features, ideas, or content) from another entity.
  • B. hasBook
    Indicates that an entity possesses, owns, or is associated with a particular book.
  • C. availableWith
    Indicates that one entity can be obtained, accessed, or used in conjunction with another entity.
  • D. hasStandingOrders
    Indicates that an entity has pre-authorized, recurring instructions or arrangements in place to be executed automatically under specified conditions.
  • E. hasUser
    Indicates that an entity is associated with or linked to a specific user.
  • 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_69a88aa84bdc819086df50e9c20b301e completed March 4, 2026, 7:40 p.m.
NER Named-entity recognition batch_69abc0913f1c8190ac9cfeb0f1c84a76 completed March 7, 2026, 6:07 a.m.
NED1 Entity disambiguation (via context triple) batch_69ae71ba743081908e2697374e710681 completed March 9, 2026, 7:07 a.m.
PD Predicate disambiguation batch_69abbdafc07881909101266a33ae7031 completed March 7, 2026, 5:54 a.m.
Created at: March 4, 2026, 7:47 p.m.