Triple
T34641078
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Lord of Winterfell |
E889557
|
entity |
| Predicate | swornBannermenInclude |
P179556
|
FINISHED |
| Object | House Umber |
—
|
NE NERFINISHED |
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: House Umber | Statement: [Lord of Winterfell, swornBannermenInclude, House Umber]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: swornBannermenInclude Context triple: [Lord of Winterfell, swornBannermenInclude, House Umber]
-
A.
swornBrother
Indicates a relationship where two or more individuals have formally pledged brotherhood to each other, typically through an oath signifying deep loyalty and mutual support.
-
B.
swornLordsInclude
Indicates that a specified group or collection of sworn lords contains or includes a particular lord as a member.
-
C.
swornSword
Indicates a formal oath of loyalty in which one entity pledges to serve and protect another as their sworn sword.
-
D.
swornHouse
Indicates a formal allegiance or oath of loyalty established between one party and a particular house or ruling family.
-
E.
hasSwornType
Indicates that one entity has formally pledged or committed to a specific type, category, or classification of something.
- F. None of above. chosen
Provenance (4 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_69f349d724848190b63ad3407e0006d9 |
completed | April 30, 2026, 12:23 p.m. |
| NER | Named-entity recognition | batch_69f722c1bc648190a79bfdc722dcaaa4 |
completed | May 3, 2026, 10:26 a.m. |
| PD | Predicate disambiguation | batch_69f72157af108190880317a62e634bb0 |
completed | May 3, 2026, 10:20 a.m. |
| PDg | Predicate description generation | batch_69f7221bc57c819085c1464a45e61b2f |
completed | May 3, 2026, 10:23 a.m. |
Created at: May 1, 2026, 2:04 a.m.