Triple

T23505065
Position Surface form Disambiguated ID Type / Status
Subject Chamling language E572258 entity
Predicate neighboringLanguage P16383 FINISHED
Object Sampang language 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: Sampang language | Statement: [Chamling language, neighboringLanguage, Sampang language]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Sampang language
Context triple: [Chamling language, neighboringLanguage, Sampang language]
  • A. Sampang language chosen
    The Sampang language is a Kiranti language spoken by the Sampang ethnic group in eastern Nepal.
  • B. Sampit language
    The Sampit language is an Austronesian language of the Barito group spoken by communities in the Sampit region of Central Kalimantan, Indonesia.
  • C. Kalumpang language
    The Kalumpang language is an Austronesian language of Sulawesi, Indonesia, belonging to the South Sulawesi subgroup and closely associated with the Toraja linguistic area.
  • D. Sangpang language
    The Sangpang language is a lesser-known Kiranti language spoken by an indigenous community in eastern Nepal.
  • E. Sambal language
    The Sambal language is an Austronesian language spoken by the Sambal people of western Luzon in the Philippines, particularly in the Zambales region.
  • 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_69e245b5e4208190bac8a6509867e394 completed April 17, 2026, 2:37 p.m.
NER Named-entity recognition batch_69f1a8ff97c88190a67f787e1674619e completed April 29, 2026, 6:45 a.m.
Created at: April 17, 2026, 6:07 p.m.