Triple
T35051167
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Blades |
E1011331
|
entity |
| Predicate | loyaltyPrinciple |
P101827
|
FINISHED |
| Object | service to the Dragonborn Emperor |
—
|
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: service to the Dragonborn Emperor | Statement: [Blades, loyaltyPrinciple, service to the Dragonborn Emperor]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: loyaltyPrinciple Context triple: [Blades, loyaltyPrinciple, service to the Dragonborn Emperor]
-
A.
loyaltyDimension
Indicates the degree or aspect of loyalty characterizing the relationship between entities.
-
B.
isLoyalTo
Indicates that one entity consistently supports, respects, or remains faithful to another entity.
-
C.
loyaltyReason
chosen
Indicates the reason or motivation behind one entity’s loyalty or allegiance to another.
-
D.
loyaltyMechanism
Indicates a mechanism or process through which loyalty is established, maintained, or reinforced between entities.
-
E.
loyaltyIncentive
Indicates a relationship where benefits or rewards are provided to encourage or recognize continued commitment or repeat engagement.
- 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_69f76dcfdda48190b1ebae5da8b54f12 |
completed | May 3, 2026, 3:46 p.m. |
| NER | Named-entity recognition | batch_69f785ce33448190bb40272ccb52ccda |
completed | May 3, 2026, 5:28 p.m. |
| PD | Predicate disambiguation | batch_69f7841812f081909d878955d114088e |
completed | May 3, 2026, 5:21 p.m. |
Created at: May 3, 2026, 4:01 p.m.