Triple
T10385356
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Imperial eagle of the Holy Roman Empire |
E244745
|
entity |
| Predicate | tinctureOfEagle |
P93911
|
FINISHED |
| Object | sable |
—
|
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: sable | Statement: [Imperial eagle of the Holy Roman Empire, tinctureOfEagle, sable]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: tinctureOfEagle Context triple: [Imperial eagle of the Holy Roman Empire, tinctureOfEagle, sable]
-
A.
tinctureOfLion
Indicates a relationship where something is a medicinal or alchemical preparation (a “tincture”) derived from or associated with a lion.
-
B.
tinctureOfAxe
Indicates that one entity is a tincture (medicinal or extract preparation) derived from or associated with an axe.
-
C.
tinctureOfField
Indicates that one entity is a tincture (medicinal extract or solution) derived from, based on, or primarily composed of another entity representing a field or source material.
-
D.
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.
-
E.
tressureTincture
Indicates the color or pattern (tincture) applied specifically to a tressure in heraldic design.
- 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_69d381b5116081908d85227bab6d3c0c |
completed | April 6, 2026, 9:49 a.m. |
| NER | Named-entity recognition | batch_69d4e9a42e748190b10fa7b4ca006bad |
completed | April 7, 2026, 11:25 a.m. |
| PD | Predicate disambiguation | batch_69d4dfb0e7a88190bec0b7a52c70dfe2 |
completed | April 7, 2026, 10:42 a.m. |
| PDg | Predicate description generation | batch_69d4e91ce2008190af252c140370b7f2 |
completed | April 7, 2026, 11:23 a.m. |
Created at: April 6, 2026, 12:04 p.m.