Triple
T11501686
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Cossack sabers (shashka) |
E272677
|
entity |
| Predicate | wornPosition |
P99826
|
FINISHED |
| Object | edge up in the scabbard |
—
|
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: edge up in the scabbard | Statement: [Cossack sabers (shashka), wornPosition, edge up in the scabbard]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: wornPosition Context triple: [Cossack sabers (shashka), wornPosition, edge up in the scabbard]
-
A.
wornAt
Indicates that an item is being worn on a specific part of the body or at a particular time or event.
-
B.
wornFor
Indicates that an item is worn for a particular purpose, function, or occasion.
-
C.
wornAs
Indicates that one entity is used or put on as clothing, an accessory, or a wearable item by another entity.
-
D.
wornAtLocation
Indicates that an item is being worn on or at a specific physical location on a body or object.
-
E.
wornOver
Indicates that one item of clothing or accessory is positioned on top of and covering another item when worn.
- 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_69d6aae2c3748190bed2ea50dfb160dc |
completed | April 8, 2026, 7:22 p.m. |
| NER | Named-entity recognition | batch_69d85de55cbc8190be71c2d03dc044f2 |
completed | April 10, 2026, 2:18 a.m. |
| PD | Predicate disambiguation | batch_69d808736c5c8190899b5b3b2e797f65 |
completed | April 9, 2026, 8:13 p.m. |
| PDg | Predicate description generation | batch_69d822ef46988190a1c360da4ee14fef |
completed | April 9, 2026, 10:06 p.m. |
Created at: April 8, 2026, 9:36 p.m.