Triple
T27112263
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kan |
E686744
|
entity |
| Predicate | hasCognateOrVariant |
P197948
|
FINISHED |
| Object | Kaan |
—
|
NE NERFINISHED |
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: Kaan | Statement: [Kan, hasCognateOrVariant, Kaan]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasCognateOrVariant Context triple: [Kan, hasCognateOrVariant, Kaan]
-
A.
hasCognate
Indicates that two linguistic forms in different languages share a common historical origin, typically descending from the same ancestral word.
-
B.
hasCognateSets
Indicates that two or more linguistic items belong to the same set of cognates, sharing a common historical origin across related languages.
-
C.
cognateOf
Indicates that two linguistic forms share a common historical origin, typically descending from the same ancestral word.
-
D.
nameCognateOf
Indicates that two names share a common linguistic origin or form, typically due to derivation from the same root or historical source.
-
E.
possibleCognateWith
Indicates a relationship where one term is considered a potential cognate of another, suggesting they may share a common historical linguistic origin.
- F. None of above. chosen
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_69ef148accd48190b6ed6e13a15f2a4f |
completed | April 27, 2026, 7:47 a.m. |
| NER | Named-entity recognition | batch_69febce5877c8190a5e000ef5331ec88 |
completed | May 9, 2026, 4:49 a.m. |
| PD | Predicate disambiguation | batch_69febad1cd588190abc7686bcb39a371 |
completed | May 9, 2026, 4:40 a.m. |
| PDg | Predicate description generation | batch_69febce420b081908e1c052751a22b1f |
completed | May 9, 2026, 4:49 a.m. |
Created at: April 27, 2026, 8:54 a.m.