Triple
T33737479
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Second Sons |
E864458
|
entity |
| Predicate | allegianceChange |
P128974
|
FINISHED |
| Object | from Yunkai to Daenerys Targaryen |
—
|
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: from Yunkai to Daenerys Targaryen | Statement: [Second Sons, allegianceChange, from Yunkai to Daenerys Targaryen]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: allegianceChange Context triple: [Second Sons, allegianceChange, from Yunkai to Daenerys Targaryen]
-
A.
changeOfAllegiance
chosen
Indicates a shift in loyalty or support from one party, group, or cause to another.
-
B.
allegianceChangeMotivation
Indicates the reason or driving factor behind an entity’s decision to change its allegiance from one side, group, or cause to another.
-
C.
hadAllegiance
Indicates that an entity was loyally committed or formally bound in support or service to another entity, such as a person, group, or cause.
-
D.
allegiance
Indicates a relationship where one entity is loyal, committed, or obligated in support or service to another entity.
-
E.
allegianceBeforeRule
Indicates that one party’s allegiance or loyalty to another existed prior to the latter’s assumption of rule or authority.
- 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_69f3498b24b8819096a65009e521d0e1 |
completed | April 30, 2026, 12:22 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 1, 2026, 1:44 a.m.