Triple
T37471371
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Aspirant’s Rest |
E931159
|
entity |
| Predicate | associatedCovenant |
P58660
|
FINISHED |
| Object | Kyrian Covenant |
E273808
|
NE 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: Kyrian Covenant | Statement: [Aspirant’s Rest, associatedCovenant, Kyrian Covenant]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: associatedCovenant Context triple: [Aspirant’s Rest, associatedCovenant, Kyrian Covenant]
-
A.
relatedCovenant
chosen
Indicates a relationship in which one covenant is connected to, associated with, or derived from another covenant.
-
B.
covenantAssociation
Indicates a formal, binding relationship or agreement that associates entities under shared obligations, promises, or terms.
-
C.
covenantWith
Indicates a formal, binding agreement or promise established between two or more parties.
-
D.
hasCovenants
Indicates that one entity is bound by or associated with formal covenants, agreements, or binding promises in relation to another entity or context.
-
E.
covenantAdopted
Indicates that a covenant has been formally accepted and put into effect by the relevant party or parties.
- F. None of above.
Provenance (4 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_69f76ec2af148190897d101070d7f415 |
completed | May 3, 2026, 3:50 p.m. |
| NER | Named-entity recognition | batch_6a037c8efcd4819088c2aeead65d93df |
completed | May 12, 2026, 7:16 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a417107452481908ecaf3a4c1767be4 |
completed | June 28, 2026, 7:07 p.m. |
| PD | Predicate disambiguation | batch_6a037a13a1308190a202df66f4781855 |
completed | May 12, 2026, 7:05 p.m. |
Created at: May 3, 2026, 4:17 p.m.