Triple

T21064772
Position Surface form Disambiguated ID Type / Status
Subject Ikhwan tribal levies E518937 entity
Predicate location P40 FINISHED
Object Nejd 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: Nejd | Statement: [Ikhwan tribal levies, location, Nejd]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Nejd
Context triple: [Ikhwan tribal levies, location, Nejd]
  • A. Nejd chosen
    Nejd is a vast central region of the Arabian Peninsula that historically served as the heartland of the Saudi state and the birthplace of its ruling dynasty.
  • B. Naju
    Naju is a historic city in South Korea known for its pear cultivation and location in the southwestern province of South Jeolla.
  • C. Nieste
    Nieste is a small settlement located within Germany's historic Westphalia region.
  • D. Nied
    Nied is a district of Frankfurt am Main in Germany, located along the River Main and known for its mix of residential areas and green spaces.
  • E. Nechtan
    Nechtan is a figure from Irish mythology, often depicted as a water or river deity associated with sacred wells and the goddess Boann.
  • 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_69e0b505ef108190b25dd4033e2ff7eb completed April 16, 2026, 10:08 a.m.
NER Named-entity recognition batch_69e6feb29e388190a80fa969a4daa606 completed April 21, 2026, 4:36 a.m.
Created at: April 16, 2026, 2:44 p.m.