Triple

T17108979
Position Surface form Disambiguated ID Type / Status
Subject Abdullah Khan Kala E415174 entity
Predicate namedAfter P63 FINISHED
Object Abdullah Khan E415174 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: Abdullah Khan | Statement: [Abdullah Khan Kala, namedAfter, Abdullah Khan]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Abdullah Khan
Context triple: [Abdullah Khan Kala, namedAfter, Abdullah Khan]
  • A. Abdul Khan
    Abdul Khan was one of the individuals killed in the 1987 Hungerford massacre, a mass shooting in Berkshire, England.
  • B. Abdullah Khan Kala chosen
    Abdullah Khan Kala is a historic fortress complex located in the ancient oasis city of Merv in present-day Turkmenistan.
  • C. Khudayar Khan
    Khudayar Khan was a 19th-century ruler of the Kokand Khanate in Central Asia, known for his turbulent reign marked by internal strife and increasing Russian influence in the region.
  • D. Mohammad Yaqub Khan
    Mohammad Yaqub Khan was the Emir of Afghanistan in the late 19th century, best known for signing the Treaty of Gandamak with the British during the Second Anglo-Afghan War.
  • E. Jamal Shah
    Jamal Shah is a historical figure interred at the Makli Necropolis, one of the world’s largest and most significant funerary sites in Sindh, Pakistan.
  • 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_69d886d090cc8190a39cb94992586905 completed April 10, 2026, 5:12 a.m.
NER Named-entity recognition batch_69e3dc2906a081909d0d43cf04319f52 completed April 18, 2026, 7:31 p.m.
NED1 Entity disambiguation (via context triple) batch_6a014145f7988190803d5c5e4f2705b0 completed May 11, 2026, 2:39 a.m.
Created at: April 10, 2026, 5:35 a.m.