Triple
T20608853
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Wiglaf |
E506390
|
entity |
| Predicate | loyaltyContrastWith |
P32882
|
FINISHED |
| Object | other Geatish thanes who flee |
—
|
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: other Geatish thanes who flee | Statement: [Wiglaf, loyaltyContrastWith, other Geatish thanes who flee]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: loyaltyContrastWith Context triple: [Wiglaf, loyaltyContrastWith, other Geatish thanes who flee]
-
A.
loyaltyConflict
chosen
Indicates a situation where an entity’s loyalties to different people, groups, or principles are in tension or opposition, creating a conflict in choosing whom or what to support.
-
B.
loyaltyReason
Indicates the reason or motivation behind one entity’s loyalty or allegiance to another.
-
C.
loyaltyDimension
Indicates the degree or aspect of loyalty characterizing the relationship between entities.
-
D.
isLoyalTo
Indicates that one entity consistently supports, respects, or remains faithful to another entity.
-
E.
loyaltyRevealedIn
Indicates that an entity’s loyalty becomes evident or is demonstrated through a particular situation, action, or context.
- 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_69e0b4bb2b4081908fa4a72444120f35 |
completed | April 16, 2026, 10:06 a.m. |
| NER | Named-entity recognition | batch_69e6aad5e53c8190b0add34ce9b31d57 |
completed | April 20, 2026, 10:38 p.m. |
| PD | Predicate disambiguation | batch_69e5a00c43308190b7ea58d559257e07 |
completed | April 20, 2026, 3:39 a.m. |
Created at: April 16, 2026, 11:41 a.m.