Triple
T12709366
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ricardo |
E303673
|
entity |
| Predicate | hasIPAInEuropeanPortuguese |
P56902
|
FINISHED |
| Object | /ʁiˈkaɾðu/ |
—
|
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: /ʁiˈkaɾðu/ | Statement: [Ricardo, hasIPAInEuropeanPortuguese, /ʁiˈkaɾðu/]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasIPAInEuropeanPortuguese Context triple: [Ricardo, hasIPAInEuropeanPortuguese, /ʁiˈkaɾðu/]
-
A.
IPAInEuropeanPortuguese
chosen
Indicates that a given word or expression is represented using its International Phonetic Alphabet (IPA) transcription as pronounced in European Portuguese.
-
B.
hasIPA
Indicates that an entity is associated with a specific International Phonetic Alphabet (IPA) transcription representing its pronunciation.
-
C.
IPAInBrazilianPortuguese
Indicates that something represents or is expressed using the International Phonetic Alphabet (IPA) as used for Brazilian Portuguese pronunciation.
-
D.
isLusophoneSurname
Indicates that a surname belongs to or is commonly used in Portuguese-speaking (Lusophone) cultures.
-
E.
hasPortugueseNameMeaning
Indicates that an entity has a Portuguese name whose semantic meaning is being specified or referenced.
- 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_69d7bdf084148190ab9d513dc0735af4 |
completed | April 9, 2026, 2:55 p.m. |
| NER | Named-entity recognition | batch_69d96207b2d881908314efc3e350aa78 |
completed | April 10, 2026, 8:48 p.m. |
| PD | Predicate disambiguation | batch_69d960c088dc8190b0e63312c54e4c6c |
completed | April 10, 2026, 8:42 p.m. |
Created at: April 9, 2026, 5:23 p.m.