Triple

T14073101
Position Surface form Disambiguated ID Type / Status
Subject Najaf International Airport E338661 entity
Predicate namedAfter P63 FINISHED
Object city of Najaf E67251 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: city of Najaf | Statement: [Najaf International Airport, namedAfter, city of Najaf]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: city of Najaf
Context triple: [Najaf International Airport, namedAfter, city of Najaf]
  • A. Najaf chosen
    Najaf is a major Iraqi city revered as a holy center of Shia Islam and home to the Imam Ali Shrine.
  • B. Hawza of Najaf
    The Hawza of Najaf is one of the most important Shia Islamic seminaries in the world, renowned as a leading center for advanced religious scholarship and clerical training.
  • C. Najaf Governorate
    Najaf Governorate is an administrative region in central Iraq that includes the holy city of Najaf, a major center of Shia Islam and religious scholarship.
  • D. Baqubah
    Baqubah is a city in eastern Iraq that serves as the capital of Diyala Governorate and lies northeast of Baghdad.
  • E. City of Medina
    The City of Medina is a small, affluent residential community in King County, Washington, located on the eastern shore of Lake Washington across from Seattle.
  • 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_69d81c687b0c819087fd9ed4198403f8 completed April 9, 2026, 9:38 p.m.
NER Named-entity recognition batch_69de5c5bc49881909012b66fa451f495 completed April 14, 2026, 3:25 p.m.
NED1 Entity disambiguation (via context triple) batch_69fcb66eeb248190b73e992ab6b9af82 completed May 7, 2026, 3:57 p.m.
Created at: April 9, 2026, 10:21 p.m.