Triple

T7219266
Position Surface form Disambiguated ID Type / Status
Subject German East Africa E150213 entity
Predicate majorPort P528 FINISHED
Object Tanga E374023 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: Tanga | Statement: [German East Africa, majorPort, Tanga]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Tanga
Context triple: [German East Africa, majorPort, Tanga]
  • A. Mambasa
    Mambasa is a town and administrative center located in the forested Ituri region of northeastern Democratic Republic of the Congo.
  • B. Tanga Region chosen
    Tanga Region is a coastal administrative region in northeastern Tanzania known for its port city of Tanga, Indian Ocean shoreline, and proximity to the Usambara Mountains.
  • C. Takrur
    Takrur was an early West African kingdom located in the Senegal River valley, known for its role in trans-Saharan trade and its early adoption of Islam.
  • D. Malaweg
    Malaweg is a Philippine language of northern Luzon, considered a variety or closely related member of the Ibanag language group.
  • E. Bashenga
    Bashenga is a legendary Wakandan warrior and the first Black Panther, revered as the founder of the Panther cult and an ancestor of T'Challa in Marvel Comics.
  • 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_69c687effb44819092b95d07d0368c9f completed March 27, 2026, 1:36 p.m.
NER Named-entity recognition batch_69c6e9b1a7908190bd215ffb84592e32 completed March 27, 2026, 8:33 p.m.
NED1 Entity disambiguation (via context triple) batch_69c7cc014fb88190818e12b7abe90c0a completed March 28, 2026, 12:39 p.m.
Created at: March 27, 2026, 2:53 p.m.