Triple

T12696099
Position Surface form Disambiguated ID Type / Status
Subject Salang Tunnel E303337 entity
Predicate connects P390 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: [Salang Tunnel, connects, Kabul]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Kabul
Context triple: [Salang Tunnel, connects, 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. Mazar-i-Sharif
    Mazar-i-Sharif is a major city in northern Afghanistan known for its strategic importance, ethnic diversity, and the revered Blue Mosque, making it a focal point in the country’s political and military conflicts.
  • D. Kunduz
    Kunduz is a strategically important city in northern Afghanistan known for its contested control during the Afghan conflict and its role as a regional commercial and transport hub.
  • E. Jalalabad, Afghanistan
    Jalalabad, Afghanistan is a major city in eastern Afghanistan near the Khyber Pass, known as a historic cultural and trade center of the region.
  • 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_69d7bdef90d48190b46b88270e780946 completed April 9, 2026, 2:55 p.m.
NER Named-entity recognition batch_69d961ebd17081909f983567e4b36533 completed April 10, 2026, 8:47 p.m.
NED1 Entity disambiguation (via context triple) batch_69f67c7c4c608190a1786accf8d86141 completed May 2, 2026, 10:36 p.m.
Created at: April 9, 2026, 5:22 p.m.