Triple
T14780709
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | The Others |
E347380
|
entity |
| Predicate | consideredMythBy |
P54696
|
FINISHED |
| Object | most people in the Seven Kingdoms |
—
|
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 people in the Seven Kingdoms | Statement: [The Others, consideredMythBy, most people in the Seven Kingdoms]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: consideredMythBy Context triple: [The Others, consideredMythBy, most people in the Seven Kingdoms]
-
A.
usesMythOf
Indicates that one entity employs or invokes a myth or mythical narrative about another entity as part of its actions, explanations, or representations.
-
B.
consideredHeresyBy
Indicates that a belief, practice, or doctrine is judged to be heretical by a particular authority, group, or tradition.
-
C.
consideredHeresySince
Indicates that something has been officially regarded as heretical starting from a specified point in time.
-
D.
mythologized
chosen
Indicates that one entity has been turned into or treated as a mythic, legendary, or highly idealized figure or story by another.
-
E.
expandsMythologyOf
Indicates that one entity broadens, enriches, or adds new elements to the mythological background or lore associated with another entity.
- 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_69d822e9b9e08190bedcc31a163fda82 |
completed | April 9, 2026, 10:06 p.m. |
| NER | Named-entity recognition | batch_69deca9c7cac8190ba900df95e42e318 |
completed | April 14, 2026, 11:15 p.m. |
| PD | Predicate disambiguation | batch_69de8c090d1081909b5a9bf437499d6c |
completed | April 14, 2026, 6:48 p.m. |
Created at: April 10, 2026, 1:31 a.m.