Triple
T16333991
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | María Isabel Verdú Rollán |
E396627
|
entity |
| Predicate | hasGivenName |
P17
|
FINISHED |
| Object | María Isabel |
E396627
|
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: María Isabel | Statement: [María Isabel Verdú Rollán, hasGivenName, María Isabel]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: María Isabel Context triple: [María Isabel Verdú Rollán, hasGivenName, María Isabel]
-
A.
María Isabel
chosen
María Isabel is the birth name of Spanish actress Maribel Verdú, known for her prominent roles in films such as "Y Tu Mamá También" and "Pan's Labyrinth."
-
B.
María Isabel
María Isabel, better known as Chábeli Iglesias, is a Spanish journalist and television personality from the prominent Iglesias entertainment family.
-
C.
María Isabel
María Isabel is a Spanish infanta (princess) of the Bourbon dynasty, known as a daughter of King Charles IV of Spain and later Queen consort of the Two Sicilies.
-
D.
María Teresa
María Teresa is the Cuban-born Grand Duchess of Luxembourg, known for her humanitarian work and role as the consort of Grand Duke Henri.
-
E.
Maria Eugenia
Maria Eugenia is a Spanish infanta, a princess of the royal family of Spain.
- 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_69e2c4e1da1081909bec6e77e6109dce |
completed | April 17, 2026, 11:40 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a006ecdffac81908ca03a88974203f9 |
completed | May 10, 2026, 11:41 a.m. |
Created at: April 10, 2026, 5:07 a.m.