Triple
T29284333
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Swanilda |
E742466
|
entity |
| Predicate | protectsRelationshipWith |
P150773
|
FINISHED |
| Object | Franz |
—
|
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: Franz | Statement: [Swanilda, protectsRelationshipWith, Franz]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: protectsRelationshipWith Context triple: [Swanilda, protectsRelationshipWith, Franz]
-
A.
protectiveRelationshipWith
chosen
Indicates a relationship in which one entity actively safeguards, defends, or looks out for the well-being of another.
-
B.
inRelationshipWith
Indicates that two entities are mutually involved in a defined personal, romantic, or partnership relationship with each other.
-
C.
showsRelationshipWith
Indicates that one entity visually or explicitly presents or demonstrates its connection or association with another entity.
-
D.
strategicRelation
Indicates a relationship where entities are connected through plans, goals, or coordinated actions intended to achieve long-term or high-level objectives.
-
E.
worksInCloseRelationshipWith
Indicates a collaborative professional relationship in which two or more entities work together closely and interact frequently to achieve shared goals.
- 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_69f09121ed8c8190b4cb27be3619c262 |
completed | April 28, 2026, 10:51 a.m. |
| NER | Named-entity recognition | batch_69f6978fe97081908fe568091ad9b159 |
completed | May 3, 2026, 12:32 a.m. |
| PD | Predicate disambiguation | batch_69f69661e6ec8190948251c7516a32ad |
completed | May 3, 2026, 12:27 a.m. |
Created at: April 28, 2026, 12:56 p.m.