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.