Triple
T4708471
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | German-speaking Lorraine |
E104449
|
entity |
| Predicate | hasToponymy |
P59103
|
FINISHED |
| Object | Germanic place names |
—
|
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: Germanic place names | Statement: [German-speaking Lorraine, hasToponymy, Germanic place names]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasToponymy Context triple: [German-speaking Lorraine, hasToponymy, Germanic place names]
-
A.
hasToponymicForm
Indicates that one entity is a toponymic (place-name-based) form or variant derived from another entity.
-
B.
isToponymic
Indicates that something is related to or derived from a place name (a toponym).
-
C.
hasToponymicUse
Indicates that a term or name is used as a toponym, i.e., as a place name or geographic designation.
-
D.
hasToponymicDerivatives
Indicates that a name or term serves as the source from which related place-based or toponymic names are derived.
-
E.
hasLanguageOfToponym
Indicates that a place name (toponym) is expressed in or associated with a particular language.
- 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_69bd43eac3c08190af7e4020c6c3704c |
completed | March 20, 2026, 12:56 p.m. |
| NER | Named-entity recognition | batch_69bd680beb508190b3d74e20e1c64405 |
completed | March 20, 2026, 3:30 p.m. |
| PD | Predicate disambiguation | batch_69bd621ddcd88190903288566f5e5dab |
completed | March 20, 2026, 3:05 p.m. |
| PDg | Predicate description generation | batch_69bd680b06e881908de87edf815f3cc0 |
completed | March 20, 2026, 3:30 p.m. |
Created at: March 20, 2026, 1:17 p.m.