Triple

T5184452
Position Surface form Disambiguated ID Type / Status
Subject Ali Abdullah Saleh E116996 entity
Predicate placeOfDeath P21 FINISHED
Object Sanaʽa, Yemen E15731 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: Sanaʽa, Yemen | Statement: [Ali Abdullah Saleh, placeOfDeath, Sanaʽa, Yemen]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Sanaʽa, Yemen
Context triple: [Ali Abdullah Saleh, placeOfDeath, Sanaʽa, Yemen]
  • A. Sanaʽa chosen
    Sanaʽa is the historic capital and one of the largest cities of Yemen, renowned for its ancient architecture and cultural significance in the Arabian Peninsula.
  • B. Sanaa
    Sanaa is a table-service restaurant at Disney’s Animal Kingdom Lodge known for its African-inspired cuisine with Indian flavors and savanna views of roaming wildlife.
  • C. SANAA
    SANAA is a renowned Japanese architectural firm, led by Kazuyo Sejima and Ryue Nishizawa, celebrated for its minimalist, light-filled designs and influential contemporary projects worldwide.
  • D. Aden
    Aden is a strategic port city in Yemen located on the Gulf of Aden, historically significant as a major maritime hub and former British colonial stronghold.
  • E. Al Hudaydah
    Al Hudaydah is a key Red Sea port city in western Yemen that serves as one of the country’s main commercial and strategic hubs.
  • 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_69bd44620ff48190bcac01782107a397 completed March 20, 2026, 12:58 p.m.
NER Named-entity recognition batch_69bd799eb90c8190b738e9478699180f completed March 20, 2026, 4:45 p.m.
NED1 Entity disambiguation (via context triple) batch_69bee085177c8190afce36104b3e3809 completed March 21, 2026, 6:16 p.m.
Created at: March 20, 2026, 1:46 p.m.