Triple
T18865599
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Freeman-Mitford family |
E461428
|
entity |
| Predicate | typeOfSurname |
P49105
|
FINISHED |
| Object | compound surname |
—
|
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: compound surname | Statement: [Freeman-Mitford family, typeOfSurname, compound surname]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: typeOfSurname Context triple: [Freeman-Mitford family, typeOfSurname, compound surname]
-
A.
hasSurnameType
chosen
Indicates that an entity’s surname belongs to a particular category or type (e.g., patronymic, toponymic, occupational).
-
B.
isSurname
Indicates that one entity is the family name (last name) of another entity.
-
C.
familyNameSuffix
Indicates that one entity is the suffix portion (such as “Jr.” or “III”) of another entity’s family name.
-
D.
namesakeType
Indicates the specific kind or category of namesake relationship that exists between two entities (for example, one being named after the other as a person, place, event, or object).
-
E.
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.
- 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_69d8dcfb7b9c8190854e7b171b98ea2e |
completed | April 10, 2026, 11:20 a.m. |
| NER | Named-entity recognition | batch_69e5c2a5074481908941fcbb3b3eefa2 |
completed | April 20, 2026, 6:07 a.m. |
| PD | Predicate disambiguation | batch_69e48d2166b88190add38de96cedc65c |
completed | April 19, 2026, 8:06 a.m. |
Created at: April 10, 2026, 11:57 a.m.