Triple
T12958082
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | House Stark |
E310069
|
entity |
| Predicate | sigil |
P15592
|
FINISHED |
| Object | Grey direwolf on a white field |
—
|
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: Grey direwolf on a white field | Statement: [House Stark, sigil, Grey direwolf on a white field]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: sigil Context triple: [House Stark, sigil, Grey direwolf on a white field]
-
A.
hasSiglum
Indicates that an entity is associated with a specific siglum, i.e., a standardized abbreviated symbol or code used to identify it.
-
B.
signature
Indicates that one entity has provided an official or personal signed endorsement, authorization, or acknowledgment on or for another entity.
-
C.
signType
Indicates the specific category or kind of sign involved in the relationship or action.
-
D.
signatureTheme
chosen
Indicates that something serves as a distinctive, defining theme strongly associated with a particular entity or context.
-
E.
signatureFeature
Indicates that one entity is a defining or characteristic feature that distinctly identifies or typifies 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_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.