Triple
T13594197
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Type 30 bayonet |
E324771
|
entity |
| Predicate | guardFeature |
P110212
|
FINISHED |
| Object | hooked quillon (early pattern) |
—
|
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: hooked quillon (early pattern) | Statement: [Type 30 bayonet, guardFeature, hooked quillon (early pattern)]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: guardFeature Context triple: [Type 30 bayonet, guardFeature, hooked quillon (early pattern)]
-
A.
guardType
Indicates the specific kind or category of guarding role or protection associated with an entity.
-
B.
guard
Indicates that one entity protects, watches over, or defends another entity or resource from harm, intrusion, or unauthorized access.
-
C.
protectsFeature
Indicates that one entity safeguards, preserves, or defends a particular feature or characteristic of another entity.
-
D.
guardMounting
Indicates the action of assigning or taking up a position for guard duty, typically as part of a scheduled security or watch rotation.
-
E.
securityFeature
Indicates that an entity provides, embodies, or is associated with a mechanism or property intended to enhance safety, protection, or defense against threats or vulnerabilities.
- 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_69d80769eaf081909d82f44e484d6113 |
completed | April 9, 2026, 8:09 p.m. |
| NER | Named-entity recognition | batch_69dbb057f1c881909a3bb77c659a724a |
completed | April 12, 2026, 2:46 p.m. |
| PD | Predicate disambiguation | batch_69dbae18eaf48190809e8b365856cde9 |
completed | April 12, 2026, 2:37 p.m. |
| PDg | Predicate description generation | batch_69dbaf9f3bdc8190838539aaef1f422b |
completed | April 12, 2026, 2:43 p.m. |
Created at: April 9, 2026, 9:49 p.m.