Triple
T28225884
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Dorothea |
E711582
|
entity |
| Predicate | hasNameDayHonoring |
P152355
|
FINISHED |
| Object | Saint Dorothea of Caesarea |
—
|
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: Saint Dorothea of Caesarea | Statement: [Dorothea, hasNameDayHonoring, Saint Dorothea of Caesarea]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasNameDayHonoring Context triple: [Dorothea, hasNameDayHonoring, Saint Dorothea of Caesarea]
-
A.
hasNameDayInSomeCountriesFor
chosen
Indicates that an entity is celebrated with a name day, in at least some countries, on behalf of or in relation to another specified entity.
-
B.
namedInHonorBy
Indicates that one entity has been used as the namesake or dedicatee by another entity, signifying that the latter is named in honor of the former.
-
C.
hasNameDay
Indicates that an entity is associated with a specific date on which its name is traditionally celebrated (a name day).
-
D.
hasNameDayOrReligiousUsage
Indicates that an entity has an associated name day celebration or is used in a religious or liturgical context.
-
E.
hasNameDayRelation
Indicates a relationship where a person’s name is associated with a specific name day or feast day in a calendar.
- 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_69efb51dfb048190ada79b745c33b363 |
completed | April 27, 2026, 7:12 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. |
Created at: April 27, 2026, 10:49 p.m.