Triple

T21982206
Position Surface form Disambiguated ID Type / Status
Subject Lawangan Dayak E542868 entity
Predicate speaks P741 FINISHED
Object Lawangan 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: Lawangan language | Statement: [Lawangan Dayak, speaks, Lawangan language]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Lawangan language
Context triple: [Lawangan Dayak, speaks, Lawangan language]
  • A. Lawangan language chosen
    The Lawangan language is an Austronesian language spoken by the Lawangan people of central Kalimantan in Indonesia.
  • B. Limba
    The Limba are one of the largest and oldest indigenous ethnic groups in Sierra Leone, known for their distinct language, cultural traditions, and historical role in the country’s northern regions.
  • C. Logba language
    The Logba language is a Niger-Congo language spoken by the Logba people of southeastern Ghana.
  • D. Blablanga language
    The Blablanga language is an Oceanic language spoken in the Solomon Islands, belonging to the Northwest Solomonic subgroup of the Austronesian language family.
  • E. Lang
    Lang is the given name of the renowned Chinese concert pianist Lang Lang, celebrated for his virtuosic technique and charismatic performances.
  • 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_69e0c48136b081908831fa907cc02e18 completed April 16, 2026, 11:14 a.m.
NER Named-entity recognition batch_69f1248de3688190a8d24cc8458851f2 completed April 28, 2026, 9:20 p.m.
Created at: April 16, 2026, 8:04 p.m.