Triple
T19515570
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Carpinetani |
E488267
|
entity |
| Predicate | associatedCountryDemonym |
P191
|
FINISHED |
| Object | Italian |
—
|
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: Italian | Statement: [Carpinetani, associatedCountryDemonym, Italian]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: associatedCountryDemonym Context triple: [Carpinetani, associatedCountryDemonym, Italian]
-
A.
associatedCountryOfficialName
Indicates that an entity is linked to the official, formal name of a specific country with which it is associated.
-
B.
countryDeJure
Indicates that one entity is the legally recognized (de jure) country having sovereignty or authority over another entity.
-
C.
administrativeDivisionOfDemonym
Indicates that a term is the demonym (name for residents) associated with a particular administrative division (such as a state, province, or region).
-
D.
hasDemonym
chosen
Indicates that one entity is the term (demonym) used to refer to the inhabitants or natives of another entity (typically a place).
-
E.
countryType
Indicates the classification or category of a country based on a specified typology (e.g., political, economic, or geographic type).
- 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_69d8e8da8bec819081f400199491ccc3 |
completed | April 10, 2026, 12:11 p.m. |
| NER | Named-entity recognition | batch_69e6359b90f08190b38359dc9e97e11c |
completed | April 20, 2026, 2:18 p.m. |
| PD | Predicate disambiguation | batch_69e4fd7bd25881908caa04eaef1f6718 |
completed | April 19, 2026, 4:06 p.m. |
Created at: April 10, 2026, 1:40 p.m.