Triple
T12300337
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | coat of arms of Russia |
E293201
|
entity |
| Predicate | orientationOfEagleHeads |
P104341
|
FINISHED |
| Object | one head facing west |
—
|
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: one head facing west | Statement: [coat of arms of Russia, orientationOfEagleHeads, one head facing west]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: orientationOfEagleHeads Context triple: [coat of arms of Russia, orientationOfEagleHeads, one head facing west]
-
A.
mainStatueOrientation
Indicates the directional orientation or facing of the primary statue in a given context or setting.
-
B.
fossilOrientation
Indicates the spatial alignment or directional positioning of a fossil relative to a reference frame or surrounding features.
-
C.
orientationInFlag
Indicates the spatial orientation or alignment of an entity as it appears within a flag.
-
D.
boarsHeadsOrientation
Indicates the spatial direction or facing alignment of boars’ heads relative to a reference frame or to each other.
-
E.
eagleHeads
Indicates that one entity is the head or leader of another entity, in a manner metaphorically associated with an eagle (e.g., primary, dominant, or top-level authority).
- 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_69d6ab6a2b50819082f6aedd32ed608a |
completed | April 8, 2026, 7:24 p.m. |
| NER | Named-entity recognition | batch_69d93f621570819091ee1db2609233ea |
completed | April 10, 2026, 6:20 p.m. |
| PD | Predicate disambiguation | batch_69d93ec02c008190a56aae60a3d9eff6 |
completed | April 10, 2026, 6:17 p.m. |
| PDg | Predicate description generation | batch_69d93f607a88819089e89fd263ae9937 |
completed | April 10, 2026, 6:20 p.m. |
Created at: April 8, 2026, 9:53 p.m.