Triple

T9247516
Position Surface form Disambiguated ID Type / Status
Subject Kurdistan Regional Government E222233 entity
Predicate capital P234 FINISHED
Object Erbil E67752 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: Erbil | Statement: [Kurdistan Regional Government, capital, Erbil]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Erbil
Context triple: [Kurdistan Regional Government, capital, Erbil]
  • A. Erbil chosen
    Erbil is the capital and largest city of the Kurdistan Region in northern Iraq, known as one of the world’s oldest continuously inhabited urban centers.
  • B. Mosul
    Mosul is a major historic city in northern Iraq, known as a cultural and economic center on the Tigris River.
  • C. Duhok
    Duhok is a city in the Kurdistan Region of Iraq, known as a growing cultural and economic center surrounded by mountains near the Turkish and Syrian borders.
  • D. Kirkuk
    Kirkuk is a historically significant, oil-rich and ethnically diverse city in northern Iraq that has long been a focal point of political and territorial disputes.
  • E. Tikrit
    Tikrit is a city in northern Iraq best known as the hometown of former president Saddam Hussein and a focal point in recent Iraqi history.
  • 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_69ca841d2b18819089f9faf5b2c2aec0 completed March 30, 2026, 2:09 p.m.
NER Named-entity recognition batch_69cd05f55a848190a59e7087cc07f6ef completed April 1, 2026, 11:48 a.m.
NED1 Entity disambiguation (via context triple) batch_69d0b1d046ac81908deffb4215bbeb82 completed April 4, 2026, 6:38 a.m.
Created at: March 30, 2026, 7:31 p.m.