Triple

T5400201
Position Surface form Disambiguated ID Type / Status
Subject Pantopia E120753 entity
Predicate previousNameOfArea P43887 FINISHED
Object Timbuktu E144680 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: Timbuktu | Statement: [Pantopia, previousNameOfArea, Timbuktu]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Timbuktu
Context triple: [Pantopia, previousNameOfArea, Timbuktu]
  • A. Timbuktu chosen
    Timbuktu is an ancient city in Mali famed as a historic center of trans-Saharan trade and Islamic scholarship.
  • B. Birgu
    Birgu is a historic fortified city in Malta, renowned for its strategic harbor position and pivotal role in the island’s military and maritime history.
  • C. Koumbi Saleh
    Koumbi Saleh was the principal urban and commercial center of the medieval West African Ghana Empire, renowned as a hub of trans-Saharan trade in gold and other goods.
  • D. Medina of Salé
    The Medina of Salé is a historic walled old town in northwestern Morocco, known for its traditional architecture, markets, and role as a former corsair stronghold opposite Rabat.
  • E. Souk El Berka
    Souk El Berka is a historic covered market in the medina of Tunis, traditionally known for its jewelry trade and distinctive architectural character.
  • 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_69bd4637b92c8190b815b6443ae4b323 completed March 20, 2026, 1:06 p.m.
NER Named-entity recognition batch_69bd8770809c8190bb387ef04ffa794c completed March 20, 2026, 5:44 p.m.
NED1 Entity disambiguation (via context triple) batch_69bf3383b360819087447e6813c45edf completed March 22, 2026, 12:10 a.m.
Created at: March 20, 2026, 2:04 p.m.