Triple

T10486713
Position Surface form Disambiguated ID Type / Status
Subject Northern Niger E247318 entity
Predicate contains P35 FINISHED
Object Bilma Erg E727099 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: Bilma Erg | Statement: [Northern Niger, contains, Bilma Erg]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Bilma Erg
Context triple: [Northern Niger, contains, Bilma Erg]
  • A. Bilma chosen
    Bilma is an oasis town in northeastern Niger, historically significant as a key stop on trans-Saharan trade routes and known for its traditional salt production.
  • B. Seyhun
    Seyhun is the historical name used in Islamic and Central Asian sources for the Syr Darya River, one of the major rivers of Central Asia.
  • C. Zübeyir
    Zübeyir is a Turkish masculine given name, notably borne by the archaeologist and ethnographer Hamit Zübeyir Koşay.
  • D. Dursunbey
    Dursunbey is a town and district in western Turkey known for its forestry, timber production, and rural character within Balıkesir Province.
  • E. Kadir
    Kadir is a masculine given name of Turkish origin commonly used in Turkey and among Turkish-speaking communities.
  • 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_69d381c309b88190af78aa681cf6a4c2 completed April 6, 2026, 9:49 a.m.
NER Named-entity recognition batch_69d5096a4d3481908e9c319f6cdce4f1 completed April 7, 2026, 1:40 p.m.
NED1 Entity disambiguation (via context triple) batch_69d8dc8c73748190b97c78af6cf142d9 completed April 10, 2026, 11:18 a.m.
Created at: April 6, 2026, 12:23 p.m.