Triple
T36296851
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Saint Mary above Minerva |
E893392
|
entity |
| Predicate | englishRenderingOf |
P31361
|
FINISHED |
| Object | Santa Maria sopra Minerva |
—
|
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: Santa Maria sopra Minerva | Statement: [Saint Mary above Minerva, englishRenderingOf, Santa Maria sopra Minerva]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: englishRenderingOf Context triple: [Saint Mary above Minerva, englishRenderingOf, Santa Maria sopra Minerva]
-
A.
englishPart
Indicates that one entity is a component, segment, or subset of another within the context of English (e.g., English text, language, or content).
-
B.
EnglishTranslation
chosen
Indicates that one expression is the English-language translation equivalent of another expression.
-
C.
EnglishVersionFeature
Indicates that the related item is a feature or aspect specifically associated with the English-language version of something.
-
D.
EnglishTranslatorOfWork
Indicates that one entity is the person who translated a specific work into English.
-
E.
equivalentEnglishForm
Indicates that two expressions share the same meaning in English, serving as equivalent linguistic forms.
- 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_69f76e4a61f0819084a2b68dbbb4efc6 |
completed | May 3, 2026, 3:48 p.m. |
| NER | Named-entity recognition | batch_69f7ba6d06f48190a71b5a2f19e2232f |
completed | May 3, 2026, 9:13 p.m. |
| PD | Predicate disambiguation | batch_69f7b9a4aad48190a62e41c5e39339d9 |
completed | May 3, 2026, 9:09 p.m. |
Created at: May 3, 2026, 4:09 p.m.