Triple
T26374858
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Stewarts of Albany |
E660866
|
entity |
| Predicate | coatOfArmsModification |
P160471
|
FINISHED |
| Object | differenced from royal Stewart arms |
—
|
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: differenced from royal Stewart arms | Statement: [Stewarts of Albany, coatOfArmsModification, differenced from royal Stewart arms]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: coatOfArmsModification Context triple: [Stewarts of Albany, coatOfArmsModification, differenced from royal Stewart arms]
-
A.
coatOfArmsVersion
Indicates the specific variant or edition of a coat of arms associated with an entity or context.
-
B.
coatOfArms
Indicates that one entity serves as the heraldic emblem or coat of arms representing another entity.
-
C.
replacedOnCoatOfArmsBy
Indicates that one element or symbol on a coat of arms has been superseded and taken the place of by another element or symbol.
-
D.
coatOfArmsType
Indicates the specific kind or category of coat of arms associated with an entity.
-
E.
coatOfArmsCaption
Indicates the descriptive text that explains or labels the depicted coat of arms.
- 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_69ee812a698881908d6a58265995fa39 |
completed | April 26, 2026, 9:18 p.m. |
| NER | Named-entity recognition | batch_69f6106e60e48190829fa2ab14bcbbdf |
completed | May 2, 2026, 2:55 p.m. |
| PD | Predicate disambiguation | batch_69f5f800fa9c8190aab0962669fde8ac |
completed | May 2, 2026, 1:11 p.m. |
| PDg | Predicate description generation | batch_69f6018ceb1c8190a6a5f84071659a96 |
completed | May 2, 2026, 1:52 p.m. |
Created at: April 26, 2026, 11 p.m.