Triple
T35648137
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Hokan hypothesis |
E1030063
|
entity |
| Predicate | includesProposedFamily |
P3600
|
FINISHED |
| Object | Karuk language family |
—
|
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: Karuk language family | Statement: [Hokan hypothesis, includesProposedFamily, Karuk language family]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: includesProposedFamily Context triple: [Hokan hypothesis, includesProposedFamily, Karuk language family]
-
A.
possibleFamily
Indicates that two entities could plausibly be related as members of the same family, though the familial relationship is not confirmed.
-
B.
containsFamily
chosen
Indicates that one entity includes or encompasses members of a particular family group within it.
-
C.
intendedFamily
Indicates that one entity is planned or designated to be part of another entity’s family or familial group in the future.
-
D.
eligibleFamily
Indicates that one entity qualifies as a family member of another under specified eligibility rules or criteria.
-
E.
allowsForFamily
Indicates that one entity enables or makes it possible for another entity to support or include family-related participation, benefits, or involvement.
- 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_69f76e0938088190a8f199631e97dec3 |
completed | May 3, 2026, 3:47 p.m. |
| NER | Named-entity recognition | batch_6a037c8d06cc8190ab6a5e18d9d2571e |
completed | May 12, 2026, 7:16 p.m. |
| PD | Predicate disambiguation | batch_6a037a04d8348190a4819666eab42c9b |
completed | May 12, 2026, 7:05 p.m. |
Created at: May 3, 2026, 4:05 p.m.