Triple
T31045786
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | House of Castile |
E791122
|
entity |
| Predicate | throughMonarch |
P170693
|
FINISHED |
| Object | Isabella I of Castile |
—
|
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: Isabella I of Castile | Statement: [House of Castile, throughMonarch, Isabella I of Castile]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: throughMonarch Context triple: [House of Castile, throughMonarch, Isabella I of Castile]
-
A.
betweenMonarch
Indicates a relationship in which one monarch stands in an intermediate or mediating position relative to two other specified monarchs or entities.
-
B.
monarchIn
Indicates that a person serves as the ruling monarch of a specified country, state, or territory.
-
C.
patronMonarch
Indicates a relationship where a monarch acts as a patron, providing support, sponsorship, or protection to another party.
-
D.
monarch
Indicates that an entity serves as the sovereign ruler (such as a king, queen, or emperor) over a state or territory.
-
E.
thirdMonarch
Indicates that the subject is the third monarch in a succession or lineage relative to a specified realm or dynasty.
- 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_69f224ca2fa881908a3ac5fedf207b90 |
completed | April 29, 2026, 3:33 p.m. |
| NER | Named-entity recognition | batch_69f694fdc95c819099e913f55cc64efb |
completed | May 3, 2026, 12:21 a.m. |
| PD | Predicate disambiguation | batch_69f690f13d7481908ddfefe95df2a1c2 |
completed | May 3, 2026, 12:04 a.m. |
| PDg | Predicate description generation | batch_69f6938244648190a553b532387b812c |
completed | May 3, 2026, 12:14 a.m. |
Created at: April 29, 2026, 8:59 p.m.