Triple
T19209124
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Fernández family |
E480310
|
entity |
| Predicate | titleTypeLinked |
P6489
|
FINISHED |
| Object | marquessate |
—
|
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: marquessate | Statement: [Fernández family, titleTypeLinked, marquessate]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: titleTypeLinked Context triple: [Fernández family, titleTypeLinked, marquessate]
-
A.
titleType
chosen
Indicates the specific category or kind of title associated with an entity (e.g., whether it is a main title, alternative title, working title, etc.).
-
B.
titleHolderType
Indicates the specific role or capacity in which an entity holds a title (e.g., owner, trustee, beneficiary).
-
C.
linkType
Indicates the specific kind or category of relationship that connects two linked entities.
-
D.
associatedTitle
Indicates that one entity has a title, designation, or formal label that is linked or relevant to another entity.
-
E.
relatedTitleHolder
Indicates that one entity holds a title or position that is related or connected to the title or position held by 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_69d8e8cb8c348190b52075823911c869 |
completed | April 10, 2026, 12:10 p.m. |
| NER | Named-entity recognition | batch_69e5f9a000188190afb762ea24bc3deb |
completed | April 20, 2026, 10:02 a.m. |
| PD | Predicate disambiguation | batch_69e4dcf22b3c8190bee02e3af946e114 |
completed | April 19, 2026, 1:47 p.m. |
Created at: April 10, 2026, 1:20 p.m.