Triple
T28039075
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Countess of Teba |
E708487
|
entity |
| Predicate | titleStyleInSpanish |
P191342
|
FINISHED |
| Object | Condesa de Teba |
—
|
NE NERFINISHED |
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: Condesa de Teba | Statement: [Countess of Teba, titleStyleInSpanish, Condesa de Teba]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: titleStyleInSpanish Context triple: [Countess of Teba, titleStyleInSpanish, Condesa de Teba]
-
A.
titleInSpanish
Indicates that one entity is the title of another entity expressed in the Spanish language.
-
B.
titleStyleInFull
Indicates that the specified title is presented in its complete, unabridged form, including all stylistic elements or formatting.
-
C.
titlesStyle
Indicates the stylistic convention or formatting applied to titles in a given context or resource.
-
D.
titleStyleAdopted
Indicates that a particular style or format for a title has been chosen and put into use for an entity.
-
E.
titleHolderStyle
Indicates the manner or format in which a title holder’s status or designation is presented or styled in relation to another entity.
- F. None of above. chosen
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_69ef9b6cf538819094a633ffa67afec1 |
completed | April 27, 2026, 5:22 p.m. |
| NER | Named-entity recognition | batch_69fcdf2394748190b35cead3e208447d |
completed | May 7, 2026, 6:51 p.m. |
| PD | Predicate disambiguation | batch_69fcdbe344ec8190a0471911952f4b82 |
completed | May 7, 2026, 6:37 p.m. |
| PDg | Predicate description generation | batch_69fcdf22ab8881908b257f16522920c5 |
completed | May 7, 2026, 6:51 p.m. |
Created at: April 27, 2026, 8:23 p.m.