Triple

T16188475
Position Surface form Disambiguated ID Type / Status
Subject Bilein E392870 entity
Predicate languageSpoken P151 FINISHED
Object Bilen language E392888 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: Bilen language | Statement: [Bilein, languageSpoken, Bilen language]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Bilen language
Context triple: [Bilein, languageSpoken, Bilen language]
  • A. Bilen language chosen
    The Bilen language is a Cushitic language spoken primarily by the Bilen people in Eritrea.
  • B. Bille language
    The Bille language is a Niger-Congo language spoken by the Bille people of the Niger Delta region in Nigeria, belonging to the Ijaw language group.
  • C. Jur Beli language
    Jur Beli is a lesser-known Nilotic language spoken by the Jur Beli people of South Sudan.
  • D. Bilua language
    The Bilua language is a Papuan language spoken primarily on Vella Lavella Island in the Solomon Islands.
  • E. Pileni language
    Pileni language is a Polynesian outlier language of the Oceanic branch spoken by communities in the Duff Islands and nearby areas of the Solomon Islands.
  • 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_69d87f1e49ac8190a311b54d32990576 completed April 10, 2026, 4:39 a.m.
NER Named-entity recognition batch_69e222d3a8e48190bdf29a633f4b0490 completed April 17, 2026, 12:08 p.m.
NED1 Entity disambiguation (via context triple) batch_69ffff0750f08190a2fce65124d8dcc0 completed May 10, 2026, 3:44 a.m.
Created at: April 10, 2026, 5:02 a.m.