Triple
T10243530
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Pérez de Guzmán |
E243657
|
entity |
| Predicate | surnameComponent |
P37098
|
FINISHED |
| Object | Pérez |
E262802
|
NE FINISHED |
How this triple was built (3 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: Pérez | Statement: [Pérez de Guzmán, surnameComponent, Pérez]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Pérez Context triple: [Pérez de Guzmán, surnameComponent, Pérez]
-
A.
Pérez
chosen
Pérez is a common Spanish-language surname widely found in Spain and Latin America.
-
B.
Peláez
Peláez is a Spanish surname of likely Galician or Asturian origin, borne by various historical and contemporary figures.
-
C.
Juan Pérez
Juan Pérez was an 18th-century Spanish naval officer and explorer notable for leading one of the first European voyages along the Pacific Northwest coast of North America.
-
D.
López
López is a common Spanish surname widely borne across Spain and Latin America.
-
E.
González
González is a common Spanish-language surname widely borne across Spain and Latin America, often associated with Iberian heritage.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: surnameComponent Context triple: [Pérez de Guzmán, surnameComponent, Pérez]
-
A.
familyName
Indicates that one entity is the family (last) name associated with another entity (typically a person).
-
B.
fatherSurname
Indicates that one entity has the same surname as, or is identified by, the family name of, the father in relation to another entity.
-
C.
hasComponentSurname
chosen
Indicates that an entity’s full name includes a specified surname as one of its component parts.
-
D.
surnameVariant
Indicates that one surname is an alternative spelling, form, or variation of another surname.
-
E.
familyNameSuffix
Indicates that one entity is the suffix portion (such as “Jr.” or “III”) of another entity’s family name.
- F. None of above.
Provenance (4 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_69d381b0f97c819085c9b45799a5fb7c |
completed | April 6, 2026, 9:49 a.m. |
| NER | Named-entity recognition | batch_69d4d328272c8190a3548d7f7f38cfc4 |
completed | April 7, 2026, 9:49 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d7fb371a408190924ccb5c51c209b7 |
completed | April 9, 2026, 7:17 p.m. |
| PD | Predicate disambiguation | batch_69d4d1ebd6c88190a1f3f4a72a99d6fe |
completed | April 7, 2026, 9:44 a.m. |
Created at: April 6, 2026, 11:25 a.m.