Triple
T35481751
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Visenya Targaryen |
E1025487
|
entity |
| Predicate | helpedUnify |
P35330
|
FINISHED |
| Object | most of Westeros |
—
|
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: most of Westeros | Statement: [Visenya Targaryen, helpedUnify, most of Westeros]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: helpedUnify Context triple: [Visenya Targaryen, helpedUnify, most of Westeros]
-
A.
aimedToUnify
Indicates an intention or effort by one entity to bring multiple entities, groups, or elements together into a single unified whole.
-
B.
unificationType
Indicates the specific manner or category in which two or more entities are combined, merged, or treated as a single unified whole.
-
C.
wasUnifiedWith
Indicates that two or more previously separate entities were brought together to form a single unified whole.
-
D.
reunifiedAs
Indicates that entities which were previously separated or divided have been brought back together into a single unified whole.
-
E.
unites
chosen
Indicates that one entity brings together multiple entities into a single, cohesive whole or shared state.
- 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_69f76dfadba0819083456aadcd6864ea |
completed | May 3, 2026, 3:47 p.m. |
| NER | Named-entity recognition | batch_69f7a225a77c81908f8953ccfeb14336 |
completed | May 3, 2026, 7:29 p.m. |
| PD | Predicate disambiguation | batch_69f7a06d4f108190bae3ab9ae431d2c7 |
completed | May 3, 2026, 7:22 p.m. |
Created at: May 3, 2026, 4:04 p.m.