Triple
T34641076
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Lord of Winterfell |
E889557
|
entity |
| Predicate | heraldicSeatType |
P111971
|
FINISHED |
| Object | castle |
—
|
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: castle | Statement: [Lord of Winterfell, heraldicSeatType, castle]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: heraldicSeatType Context triple: [Lord of Winterfell, heraldicSeatType, castle]
-
A.
heraldicCharge
Indicates that one entity serves as a heraldic charge, i.e., a symbolic figure or emblem placed on another entity’s coat of arms or shield.
-
B.
heraldicStatus
Indicates the formal standing or classification of an entity within a heraldic system, such as its rank, legitimacy, or official recognition in heraldry.
-
C.
heraldicAspect
chosen
Indicates a relationship where one entity serves as a heraldic feature, attribute, or component in the coat of arms or heraldic representation of another entity.
-
D.
coatOfArmsType
Indicates the specific kind or category of coat of arms associated with an entity.
-
E.
heraldicName
Indicates the formal name or designation assigned to a heraldic element (such as a coat of arms, charge, or symbol) within a heraldic system.
- 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_69f349d724848190b63ad3407e0006d9 |
completed | April 30, 2026, 12:23 p.m. |
| NER | Named-entity recognition | batch_69f7229234d48190a95d834c3c790f3f |
completed | May 3, 2026, 10:25 a.m. |
| PD | Predicate disambiguation | batch_69f72157af108190880317a62e634bb0 |
completed | May 3, 2026, 10:20 a.m. |
Created at: May 1, 2026, 2:04 a.m.