Triple

T697110
Position Surface form Disambiguated ID Type / Status
Subject Humayun E13916 entity
Predicate birthPlace P1 FINISHED
Object Kabul E55103 NE FINISHED

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: Kabul | Statement: [Humayun, birthPlace, Kabul]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Kabul
Context triple: [Humayun, birthPlace, Kabul]
  • A. Kabul chosen
    Kabul is the capital and largest city of Afghanistan, serving as its political, cultural, and economic center in the eastern part of the country.
  • B. Kandahar
    Kandahar is a historic city in southern Afghanistan that has long served as a major political, cultural, and commercial center in the region.
  • C. Herat
    Herat is a historic city in western Afghanistan that flourished as a major cultural and political center of the Timurid Empire and a key hub on the Silk Road.
  • D. Islamabad
    Islamabad is Pakistan’s planned, modern capital city known for its high standard of living, greenery, and role as the country’s political and administrative center.
  • E. Quetta
    Quetta is a major city in western Pakistan known as the provincial capital of Balochistan and a key commercial and military center near the Afghan border.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (3 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_69a493406c408190957eeec9048a8fb6 completed March 1, 2026, 7:28 p.m.
NER Named-entity recognition batch_69a4a0c8055881909565ebde2be8fd7a completed March 1, 2026, 8:25 p.m.
NED1 Entity disambiguation (via context triple) batch_69a64a5618348190b8ec2c7d6bd06e2b completed March 3, 2026, 2:41 a.m.
Created at: March 1, 2026, 7:36 p.m.