Triple

T10390041
Position Surface form Disambiguated ID Type / Status
Subject Eyak E244865 entity
Predicate lastNativeSpeakerDied P43860 FINISHED
Object 2008 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: 2008 | Statement: [Eyak, lastNativeSpeakerDied, 2008]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: lastNativeSpeakerDied
Context triple: [Eyak, lastNativeSpeakerDied, 2008]
  • A. lastNativeSpeakersDiedOut chosen
    Indicates that the final remaining native speakers of a language or dialect have died, resulting in the loss of native speech for that language.
  • B. lastTraditionalNativeSpeakerOftenCitedAs
    Indicates that the subject is widely regarded or referenced as the last traditional native speaker of the language or dialect in question.
  • C. hasNoNativeSpeakers
    Indicates that the language or dialect is not natively acquired as a first language by any living community.
  • D. hasApproximateNativeSpeakers
    Indicates that an entity is associated with an estimated or approximate number of people who speak it as their native language.
  • E. historicallySpokenIn
    Indicates that a language was used for spoken communication in a particular place or region during a past historical period.
  • 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_69d381b5116081908d85227bab6d3c0c completed April 6, 2026, 9:49 a.m.
NER Named-entity recognition batch_69d4e9b4f7d08190bcb16d3b4c8f22ad completed April 7, 2026, 11:25 a.m.
PD Predicate disambiguation batch_69d4dfb0e7a88190bec0b7a52c70dfe2 completed April 7, 2026, 10:42 a.m.
Created at: April 6, 2026, 12:05 p.m.