Triple

T6696455
Position Surface form Disambiguated ID Type / Status
Subject Nganasan language E152761 entity
Predicate primaryCurrentSpeakers P18995 FINISHED
Object elderly Nganasan people LITERAL 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: elderly Nganasan people | Statement: [Nganasan language, primaryCurrentSpeakers, elderly Nganasan people]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: primaryCurrentSpeakers
Context triple: [Nganasan language, primaryCurrentSpeakers, elderly Nganasan people]
  • A. currentSpeakers
    Indicates that the referenced entities are the ones who are presently speaking or holding the floor at a given moment.
  • B. primarySpeakers chosen
    Indicates the entities that are the main or most significant speakers associated with another entity (such as an event, recording, or language).
  • C. speakers
    Indicates that one or more entities produce spoken language or vocal communication, typically addressing an audience or participating in a conversation.
  • D. hasSpeakersIn
    Indicates that an entity (such as an event, conference, or session) includes or is associated with speakers located in or belonging to a specified place or group.
  • E. lastKnownSpeakers
    Indicates the people or entities most recently known to use or speak a particular language.
  • F. None of above.

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_69c6880687b08190805278b504d1c92c completed March 27, 2026, 1:37 p.m.
NER Named-entity recognition batch_69c6b5ed99e48190970805225458ce82 completed March 27, 2026, 4:53 p.m.
PD Predicate disambiguation batch_69c6ad0e1d348190af1762ea1951038e completed March 27, 2026, 4:15 p.m.
Created at: March 27, 2026, 2:05 p.m.