Triple
T3982188
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Annobonese people |
E85782
|
entity |
| Predicate | bilingualism |
P5152
|
FINISHED |
| Object | many speak both Fá d’Ambô and Spanish |
—
|
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: many speak both Fá d’Ambô and Spanish | Statement: [Annobonese people, bilingualism, many speak both Fá d’Ambô and Spanish]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: bilingualism Context triple: [Annobonese people, bilingualism, many speak both Fá d’Ambô and Spanish]
-
A.
isBilingual
chosen
Indicates that an entity is able to communicate fluently in two distinct languages.
-
B.
officialBilingualism
Indicates that a jurisdiction or institution has formally adopted two languages as having equal official status for government and public functions.
-
C.
isBilingualRegion
Indicates that a region officially uses two languages or has two predominant languages in regular use.
-
D.
bilingualName
Indicates that an entity has a name expressed in two different languages, linking the entity to its bilingual designation.
-
E.
secondLanguageSpeakers
Indicates that the referenced language is spoken as a second (non-native) language by the specified group or number of people.
- 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_69aed93908348190a26c8aaf4fab3e86 |
completed | March 9, 2026, 2:29 p.m. |
| NER | Named-entity recognition | batch_69aefa3ef7ac8190abe02f440ff83c43 |
completed | March 9, 2026, 4:50 p.m. |
| PD | Predicate disambiguation | batch_69aef8f492ac819089dbb9436dbcdd2b |
completed | March 9, 2026, 4:44 p.m. |
Created at: March 9, 2026, 3:33 p.m.