Triple
T17579958
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Duke of Shrewsbury |
E428174
|
entity |
| Predicate | notableHolderReligion |
P23795
|
FINISHED |
| Object | Roman Catholic (early life) |
—
|
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: Roman Catholic (early life) | Statement: [Duke of Shrewsbury, notableHolderReligion, Roman Catholic (early life)]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: notableHolderReligion Context triple: [Duke of Shrewsbury, notableHolderReligion, Roman Catholic (early life)]
-
A.
religiousInstitutionsNotableFor
Indicates that certain religious institutions are notable or distinguished for a particular characteristic, quality, activity, or role.
-
B.
titleHolderReligion
chosen
Indicates the religious affiliation associated with the holder of a particular title.
-
C.
religionSignificant
Indicates that a particular religion plays an important or influential role in relation to the referenced entity or context.
-
D.
religionNote
Indicates that there is an explanatory note or comment providing additional information or clarification about a subject’s religion.
-
E.
foundedReligion
Indicates that an entity established or originated a particular religion.
- 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_69d889e1030481909950e140c63255b9 |
completed | April 10, 2026, 5:25 a.m. |
| NER | Named-entity recognition | batch_69e463cdb1608190a7e249ad6531b1dc |
completed | April 19, 2026, 5:10 a.m. |
| PD | Predicate disambiguation | batch_69e3b4fd7d048190b54ee4c6155612a5 |
completed | April 18, 2026, 4:44 p.m. |
Created at: April 10, 2026, 5:50 a.m.