Triple

T3254720
Position Surface form Disambiguated ID Type / Status
Subject Kilwa Kisiwani E68268 entity
Predicate tradedWith P2914 FINISHED
Object Arabia E7627 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: Arabia | Statement: [Kilwa Kisiwani, tradedWith, Arabia]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Arabia
Context triple: [Kilwa Kisiwani, tradedWith, Arabia]
  • A. Arabian Peninsula chosen
    The Arabian Peninsula is a vast, predominantly desert region in Western Asia that is considered the historical heartland of Arab culture and the birthplace of Islam.
  • B. Saudi Arabia
    Saudi Arabia is a Middle Eastern kingdom on the Arabian Peninsula known for its vast oil reserves, custodianship of Islam’s holiest sites, and significant geopolitical influence.
  • C. Sulaymaniya
    Sulaymaniya is a sub-school within the Zaydi branch of Shia Islam, distinguished by its own specific theological and legal interpretations.
  • D. L’Algarabie
    L’Algarabie is a literary work by Spanish writer and political exile Jorge Semprún, reflecting his characteristic engagement with memory, identity, and the legacy of 20th-century European conflicts.
  • E. Assiyah
    Assiyah is the lowest of the four Kabbalistic worlds, representing the realm of physical creation and action.
  • 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_69ad858f74408190bcbd07f967cd7bd0 completed March 8, 2026, 2:19 p.m.
NER Named-entity recognition batch_69adaf65c9388190a0d74d6365ce631e completed March 8, 2026, 5:18 p.m.
NED1 Entity disambiguation (via context triple) batch_69b2e8330720819091548d7f9652003a completed March 12, 2026, 4:22 p.m.
Created at: March 8, 2026, 3:09 p.m.