Triple
T388693
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Raetic language |
E8833
|
entity |
| Predicate | notClassifiedAs |
P12860
|
FINISHED |
| Object | Indo-European language |
—
|
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: Indo-European language | Statement: [Raetic language, notClassifiedAs, Indo-European language]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: notClassifiedAs Context triple: [Raetic language, notClassifiedAs, Indo-European language]
-
A.
notRecognizedBy
Indicates that one entity does not acknowledge, accept, or formally recognize the status, authority, or validity of another entity.
-
B.
notObservedIn
Indicates that a particular entity, event, or property has not been detected, recorded, or seen within a specified context, dataset, or environment.
-
C.
notFunction
Indicates that the specified entity does not serve as a function or is not used in a functional role within the given context.
-
D.
classificationStart
Indicates the point in time or process at which a classification or categorization of an entity begins.
-
E.
protectedCategory
Indicates that one entity is classified under a legally or formally recognized group that is granted special protection from discrimination or adverse treatment.
- 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_69a2e7f55c60819097aff65ea2ca2832 |
completed | Feb. 28, 2026, 1:04 p.m. |
| NER | Named-entity recognition | batch_69a2ec5988708190aa86d9460cecf050 |
completed | Feb. 28, 2026, 1:23 p.m. |
| PD | Predicate disambiguation | batch_69a2e96960608190bdd342da9c5ddb5e |
completed | Feb. 28, 2026, 1:11 p.m. |
| PDg | Predicate description generation | batch_69a2ebac09408190be802b96bb203d5f |
completed | Feb. 28, 2026, 1:20 p.m. |
Created at: Feb. 28, 2026, 1:08 p.m.