Triple
T204326
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Coat of arms of Bermuda |
E4576
|
entity |
| Predicate | crest |
P10235
|
FINISHED |
| Object | red lion holding a shield |
—
|
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: red lion holding a shield | Statement: [Coat of arms of Bermuda, crest, red lion holding a shield]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: crest Context triple: [Coat of arms of Bermuda, crest, red lion holding a shield]
-
A.
prominence
Indicates that an entity stands out in importance, visibility, or influence relative to others within a given context.
-
B.
above
Indicates that one entity is positioned higher than another along a vertical axis, without implying direct contact.
-
C.
front
Indicates that one entity is located directly before or facing another entity along a primary viewing or movement direction.
-
D.
elevation
Indicates the vertical height or altitude of one entity relative to a reference level or another entity.
-
E.
traction
Indicates the degree to which one entity’s movement or influence effectively grips, pulls, or gains momentum relative to another entity or medium.
- 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_69a25737567c81908f9c505300239181 |
completed | Feb. 28, 2026, 2:47 a.m. |
| NER | Named-entity recognition | batch_69a25f46b4f081909e5ee3718109a71f |
completed | Feb. 28, 2026, 3:21 a.m. |
| PD | Predicate disambiguation | batch_69a25b4b42ec8190bef16bbbdd30a742 |
completed | Feb. 28, 2026, 3:04 a.m. |
| PDg | Predicate description generation | batch_69a25f4602c081909e89de233cbc5670 |
completed | Feb. 28, 2026, 3:21 a.m. |
Created at: Feb. 28, 2026, 2:51 a.m.