Triple

T22951468
Position Surface form Disambiguated ID Type / Status
Subject Lenje language E570029 entity
Predicate glottologName P6521 FINISHED
Object Lenje NE NERFINISHED

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: Lenje | Statement: [Lenje language, glottologName, Lenje]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Lenje
Context triple: [Lenje language, glottologName, Lenje]
  • A. Lenje chosen
    Lenje is a Bantu language spoken primarily by the Lenje people of central Zambia.
  • B. Lenjan
    Lenjan is a city in Iran’s Isfahan Province, known for its location along the Zayandeh River and its role in the region’s industrial and agricultural activities.
  • C. Lauje
    Lauje are an indigenous ethnic group of Central Sulawesi, Indonesia, known for their distinct Austronesian language and traditional agrarian lifestyle in the region’s highlands and coastal areas.
  • D. Lenehan
    Lenehan is a minor yet memorable Dublin journalist and raconteur in James Joyce’s *Ulysses*, known for his cynical wit and parasitic social habits.
  • E. Lepe
    Lepe is a small coastal area and country park on the south coast of England, known for its shingle beach, views across the Solent, and historic D-Day embarkation remains.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 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_69e2459199d08190a8184ee2aa935842 completed April 17, 2026, 2:37 p.m.
NER Named-entity recognition batch_69f181a285448190a718734fe933d51a completed April 29, 2026, 3:57 a.m.
Created at: April 17, 2026, 3:46 p.m.