Triple
T37675271
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Arms of Russell, Dukes of Bedford |
E938074
|
entity |
| Predicate | supporterCollarTincture |
P23238
|
FINISHED |
| Object | or |
—
|
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: or | Statement: [Arms of Russell, Dukes of Bedford, supporterCollarTincture, or]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: supporterCollarTincture Context triple: [Arms of Russell, Dukes of Bedford, supporterCollarTincture, or]
-
A.
supporterTincture
chosen
Indicates that a heraldic supporter (a figure holding or standing beside the shield) bears a specified tincture (color or pattern).
-
B.
supporterCollar
Indicates that one entity serves as a collar-like structural element that supports or stabilizes another entity.
-
C.
tinctureOfCross
Indicates that something is a tincture (heraldic color or pattern) specifically applied to a cross in a coat of arms or similar symbolic design.
-
D.
tinctureOfBear
Indicates a relationship where a substance is a tincture derived from or made using bear (or bear-related material) as its primary source.
-
E.
chiefTincture
Indicates that one entity serves as the primary or dominant coloring or tonal quality in relation to 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_69f76ed7b1408190ba8c93c53cb8becf |
completed | May 3, 2026, 3:50 p.m. |
| NER | Named-entity recognition | batch_6a037c8efcd4819088c2aeead65d93df |
completed | May 12, 2026, 7:16 p.m. |
| PD | Predicate disambiguation | batch_6a037a1772e48190ba738c6d11b321e2 |
completed | May 12, 2026, 7:05 p.m. |
Created at: May 3, 2026, 4:18 p.m.