Triple
T16329382
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ines |
E396507
|
entity |
| Predicate | hasSpellingVariant |
P457
|
FINISHED |
| Object | Inês |
E396508
|
NE 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: Inês | Statement: [Ines, hasSpellingVariant, Inês]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Inês Context triple: [Ines, hasSpellingVariant, Inês]
-
A.
Inês
chosen
Inês is a Portuguese given name, equivalent to Agnes, commonly used for women in Portuguese-speaking countries.
-
B.
Inês de Castro
Inês de Castro is a tragic figure from 14th-century Portuguese history and legend, famed as the posthumously recognized queen whose love affair with King Pedro I inspired numerous works of art and literature.
-
C.
Ana de Castro
Ana de Castro was a Spanish noblewoman known primarily as the wife of Luis Colón de Toledo, a descendant of Christopher Columbus.
-
D.
Inés
Inés is a feminine given name, especially common in Spanish-speaking countries, derived from the name Agnes.
-
E.
Inés de Suárez
Inés de Suárez is a station on Line 6 of the Santiago Metro in Santiago, Chile.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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_69d87f255b788190a400eba031dd85d8 |
completed | April 10, 2026, 4:40 a.m. |
| NER | Named-entity recognition | batch_69e2c4ddc5608190b24fe2e871691470 |
completed | April 17, 2026, 11:40 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a003c4ca7ac819098cae8aabfe7e395 |
completed | May 10, 2026, 8:05 a.m. |
Created at: April 10, 2026, 5:07 a.m.