Triple

T33629970
Position Surface form Disambiguated ID Type / Status
Subject Athabaskan–Eyak–Tlingit E861524 entity
Predicate includesLanguageBranch P2177 FINISHED
Object Northern Athabaskan E70629 NE 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: Northern Athabaskan | Statement: [Athabaskan–Eyak–Tlingit, includesLanguageBranch, Northern Athabaskan]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: includesLanguageBranch
Context triple: [Athabaskan–Eyak–Tlingit, includesLanguageBranch, Northern Athabaskan]
  • A. includesLanguage chosen
    Indicates that one entity contains, supports, or makes use of a specified language as part of its content, functionality, or representation.
  • B. possibleLanguageBranch
    Indicates that one entity may belong to, derive from, or be classified under the language branch represented by the other entity, without asserting this relationship as certain.
  • C. hasPrimaryLanguageBranch
    Indicates that an entity’s main or dominant language belongs to a specified language branch or family.
  • D. languageBranch
    Indicates that one language belongs to, or is classified under, a broader linguistic branch or subgroup.
  • E. includesLanguageCluster
    Indicates that one entity contains or encompasses a specific group or cluster of related languages as part of its composition or scope.
  • F. None of above.

Provenance (4 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_69f34981c54c81909b33c3fa2208a52d completed April 30, 2026, 12:22 p.m.
NER Named-entity recognition batch_6a0338d1074481909541e6150307e7f8 completed May 12, 2026, 2:27 p.m.
NED1 Entity disambiguation (via context triple) batch_6a36271510a08190960b75f75ddd7f5b completed June 20, 2026, 5:37 a.m.
PD Predicate disambiguation batch_6a03386e7da08190b533cb0e908503dd completed May 12, 2026, 2:25 p.m.
Created at: May 1, 2026, 1:41 a.m.