Triple
T16838286
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Messinesi |
E409339
|
entity |
| Predicate | subnationalIdentity |
P89204
|
FINISHED |
| Object | Sicilian |
—
|
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: Sicilian | Statement: [Messinesi, subnationalIdentity, Sicilian]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: subnationalIdentity Context triple: [Messinesi, subnationalIdentity, Sicilian]
-
A.
subnationalEntityOfOrigin
chosen
Indicates that a subnational region (such as a state, province, or city) is the place from which an entity originates or is derived.
-
B.
isSubnationalDivisionOf
Indicates that one entity is an administrative or territorial subdivision that is officially part of, and governed within the jurisdiction of, another larger political entity.
-
C.
hasSubnationalCounterpart
Indicates that an entity has a corresponding or equivalent entity at a lower (subnational) administrative level.
-
D.
betweenSubnationalUnits
Indicates a relationship that occurs or holds between two or more subnational administrative units (such as states, provinces, or regions) within a country.
-
E.
inCountrySubregion
Indicates that one location or entity is situated within a specific subregion of a country.
- 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_69d883952b048190887740a980b712ed |
completed | April 10, 2026, 4:59 a.m. |
| NER | Named-entity recognition | batch_69e3b34ed7d48190a5f8d9f03a332a22 |
completed | April 18, 2026, 4:37 p.m. |
| PD | Predicate disambiguation | batch_69e32b87b4248190aaddb05e88452356 |
completed | April 18, 2026, 6:58 a.m. |
Created at: April 10, 2026, 5:23 a.m.