Triple
T34143897
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Viserys Targaryen |
E875794
|
entity |
| Predicate | viewsOn |
P43390
|
FINISHED |
| Object | believes Westeros is his by birthright |
—
|
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: believes Westeros is his by birthright | Statement: [Viserys Targaryen, viewsOn, believes Westeros is his by birthright]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: viewsOn Context triple: [Viserys Targaryen, viewsOn, believes Westeros is his by birthright]
-
A.
viewIs
Indicates that one entity is a visual representation or perspective of another entity.
-
B.
viewOver
Indicates that one entity has a visual perspective overlooking or facing another entity, typically providing a vantage point onto it.
-
C.
viewsAs
Indicates that one entity perceives, interprets, or regards another entity in a particular way or role.
-
D.
viewOnInterest
chosen
Indicates a perspective, opinion, or stance that one entity holds regarding a particular interest or topic.
-
E.
viewOnHereafter
Indicates a subject’s beliefs, opinions, or perspective regarding the afterlife or what happens after death.
- 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_69f349aaeef08190a20e72a3fdeb7052 |
completed | April 30, 2026, 12:23 p.m. |
| NER | Named-entity recognition | batch_69f71362f1448190985a80ce7af475cb |
completed | May 3, 2026, 9:20 a.m. |
| PD | Predicate disambiguation | batch_69f7127884388190884f23d181a65d19 |
completed | May 3, 2026, 9:16 a.m. |
Created at: May 1, 2026, 1:54 a.m.