Triple
T30021212
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Stefan Nemanjić |
E762744
|
entity |
| Predicate | religiousNameOfSibling |
P34795
|
FINISHED |
| Object | Saint Sava |
—
|
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 Sava | Statement: [Stefan Nemanjić, religiousNameOfSibling, Saint Sava]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: religiousNameOfSibling Context triple: [Stefan Nemanjić, religiousNameOfSibling, Saint Sava]
-
A.
siblingCharacterName
Indicates that one character’s name is that of a sibling of another character.
-
B.
siblingOrRelative
Indicates that two entities are related to each other by blood, marriage, or family ties, including but not limited to being siblings.
-
C.
religiousNamesake
chosen
Indicates that one entity serves as the religiously significant figure, concept, or object after which the other entity is named.
-
D.
siblingPseudonymOf
Indicates that one pseudonym is used by a person who is closely associated with, but distinct from, the person using another pseudonym, in a way analogous to a sibling relationship between the identities.
-
E.
hasSiblingDeity
Indicates that one deity is a sibling (sharing at least one parent) of another deity.
- 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_69f2246ee6e48190b69e837b913b398a |
completed | April 29, 2026, 3:31 p.m. |
| NER | Named-entity recognition | batch_69fdec5ffe088190ac5505f26c6cff18 |
completed | May 8, 2026, 2 p.m. |
| PD | Predicate disambiguation | batch_69fdeae15f1c81908fc63fbc1b028d2e |
completed | May 8, 2026, 1:53 p.m. |
Created at: April 29, 2026, 6:47 p.m.