Triple
T11501680
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Cossack sabers (shashka) |
E272677
|
entity |
| Predicate | hasHilt |
P99824
|
FINISHED |
| Object | usually without guard or with minimal guard |
—
|
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: usually without guard or with minimal guard | Statement: [Cossack sabers (shashka), hasHilt, usually without guard or with minimal guard]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasHilt Context triple: [Cossack sabers (shashka), hasHilt, usually without guard or with minimal guard]
-
A.
hasApp
Indicates that an entity possesses, provides, or is associated with a particular application.
-
B.
hasMP
Indicates that an entity is represented by, or associated with, a specific Member of Parliament (MP).
-
C.
hasHoist
Indicates that one entity is equipped with or includes a hoisting mechanism or device.
-
D.
hasHook
Indicates that one entity possesses, is equipped with, or features a hook in relation to another entity or context.
-
E.
hasAndroid
Indicates that an entity possesses, is equipped with, or is associated with an Android device, system, or component.
- 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.