Triple
T369136
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kalderash |
E8228
|
entity |
| Predicate | exonymOrigin |
P4705
|
FINISHED |
| Object | Romanian word "căldărar" (cauldron maker) |
—
|
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: Romanian word "căldărar" (cauldron maker) | Statement: [Kalderash, exonymOrigin, Romanian word "căldărar" (cauldron maker)]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: exonymOrigin Context triple: [Kalderash, exonymOrigin, Romanian word "căldărar" (cauldron maker)]
-
A.
hasExonym
chosen
Indicates that one entity is known by an alternative name or designation in another language or cultural context.
-
B.
ethnonym
Indicates that one entity is the name of an ethnic group used to refer to the people associated with another entity.
-
C.
etymologyType
Indicates the specific kind or category of etymological relationship that links a term to its linguistic origin or source.
-
D.
hasDemonym
Indicates that one entity is the term (demonym) used to refer to the inhabitants or natives of another entity (typically a place).
-
E.
hasEndonym
Indicates that an entity has a name or designation used by native speakers or within its own local language or community.
- 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_69a2e7f2ec648190b42bc7db424f8109 |
completed | Feb. 28, 2026, 1:04 p.m. |
| NER | Named-entity recognition | batch_69a2ebfdb0608190b1794a871d0d237a |
completed | Feb. 28, 2026, 1:22 p.m. |
| PD | Predicate disambiguation | batch_69a2e95ede588190998fdf3a6ea90498 |
completed | Feb. 28, 2026, 1:10 p.m. |
Created at: Feb. 28, 2026, 1:08 p.m.