Triple
T22424908
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Brindisini |
E554342
|
entity |
| Predicate | usesGentilicInEnglish |
P105483
|
FINISHED |
| Object | people of Brindisi |
—
|
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: people of Brindisi | Statement: [Brindisini, usesGentilicInEnglish, people of Brindisi]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: usesGentilicInEnglish Context triple: [Brindisini, usesGentilicInEnglish, people of Brindisi]
-
A.
usesGentilicFor
chosen
Indicates that one entity refers to another using a gentilic (a demonym or term denoting origin, nationality, or regional affiliation).
-
B.
gentilicium
Indicates that an entity’s family or clan affiliation is expressed through a gentilic (family) name.
-
C.
equivalentGivenNameInEnglish
Indicates that two given names are equivalent in meaning or usage when expressed in English.
-
D.
gentilicLanguage
Indicates that a language is associated with or derived from a particular gentilic (demonym) for a people or place.
-
E.
usesPersonalNamesFrom
Indicates that one entity employs or adopts the system or set of personal names originating from another entity.
- 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_69e11e4f2d0c819091aa3558ea2ee630 |
completed | April 16, 2026, 5:37 p.m. |
| NER | Named-entity recognition | batch_69f15a2c47bc81908b8265d83fa6fb65 |
completed | April 29, 2026, 1:09 a.m. |
| PD | Predicate disambiguation | batch_69e898a327948190beee5e168006a0a7 |
completed | April 22, 2026, 9:45 a.m. |
Created at: April 16, 2026, 8:47 p.m.