Triple
T9956579
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Julian the Apostate |
E195460
|
entity |
| Predicate | spouseRelation |
P13
|
FINISHED |
| Object | daughter of Constantine the Great |
—
|
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: daughter of Constantine the Great | Statement: [Julian the Apostate, spouseRelation, daughter of Constantine the Great]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: spouseRelation Context triple: [Julian the Apostate, spouseRelation, daughter of Constantine the Great]
-
A.
spouseRelationshipContext
Indicates a marital relationship context between two entities, specifying that they are spouses or partners in a recognized marriage-like union.
-
B.
spouseType
Indicates the specific role or category of a person within a spousal relationship (e.g., husband, wife, partner).
-
C.
spouseAssociatedWith
Indicates a marital or spousal relationship or close association between two entities.
-
D.
spouseFamily
Indicates a family relationship formed through marriage, such as between a person and their spouse’s relatives.
-
E.
spouse
chosen
Indicates that two entities are married to each other in a legally or socially recognized partnership.
- 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_69ca82eaaa008190a54fa1a9f954b9ad |
completed | March 30, 2026, 2:04 p.m. |
| NER | Named-entity recognition | batch_69cdb6976b50819097a0ae347354e92c |
completed | April 2, 2026, 12:21 a.m. |
| PD | Predicate disambiguation | batch_69cd1d9ae19c819099fb3635e57c79be |
completed | April 1, 2026, 1:28 p.m. |
Created at: March 30, 2026, 8:46 p.m.