Triple

T8021064
Position Surface form Disambiguated ID Type / Status
Subject Zheng He E186741 entity
Predicate sailedTo P12804 FINISHED
Object Malindi E522404 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: Malindi | Statement: [Zheng He, sailedTo, Malindi]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Malindi
Context triple: [Zheng He, sailedTo, Malindi]
  • A. Malindi chosen
    Malindi is a historic coastal town in southeastern Kenya known for its beaches, Swahili culture, and role as a former trading port on the Indian Ocean.
  • B. Mombasa
    Mombasa is a major coastal city in Kenya known as a key regional port and historic trading hub on the Indian Ocean.
  • C. Mambasa
    Mambasa is a town and administrative center located in the forested Ituri region of northeastern Democratic Republic of the Congo.
  • D. Umtentweni
    Umtentweni is a coastal resort town on South Africa’s KwaZulu-Natal South Coast, known for its beaches, subtropical climate, and relaxed holiday atmosphere.
  • E. Gombe
    Gombe is a region in western Tanzania best known for its national park where pioneering primatologist Jane Goodall conducted her landmark chimpanzee research.
  • 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_69ca82ac7fc081909b1398cf025423af completed March 30, 2026, 2:03 p.m.
NER Named-entity recognition batch_69cb3e8d90488190b57d1e748e272061 completed March 31, 2026, 3:25 a.m.
NED1 Entity disambiguation (via context triple) batch_69cc56c82824819082e93eddc40bfad1 completed March 31, 2026, 11:20 p.m.
Created at: March 30, 2026, 5:20 p.m.