Triple
T12958137
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | House Lannister |
E310070
|
entity |
| Predicate | mottoUnofficial |
P42
|
FINISHED |
| Object | A Lannister always pays his debts |
—
|
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: A Lannister always pays his debts | Statement: [House Lannister, mottoUnofficial, A Lannister always pays his debts]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: mottoUnofficial Context triple: [House Lannister, mottoUnofficial, A Lannister always pays his debts]
-
A.
mottoOriginalLanguage
Indicates the language in which a motto was originally formulated or expressed.
-
B.
motto
chosen
Indicates that one entity serves as the guiding phrase, slogan, or maxim associated with another entity.
-
C.
mottoType
Indicates the specific category or kind of motto that characterizes the relationship between an entity and its motto.
-
D.
mottoPresent
Indicates that an entity currently has an official motto associated with it.
-
E.
mottoOriginal
Indicates that one entity is the original wording or form of another entity’s motto.
- 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_69d7bdfb57a88190836b743e2825feca |
completed | April 9, 2026, 2:55 p.m. |
| NER | Named-entity recognition | batch_69d97e59a4c88190907d05b8d57dae89 |
completed | April 10, 2026, 10:48 p.m. |
| PD | Predicate disambiguation | batch_69d97dba57988190b786ffed55687a72 |
completed | April 10, 2026, 10:46 p.m. |
Created at: April 9, 2026, 5:44 p.m.