Triple
T10423731
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Nashorn |
E245730
|
entity |
| Predicate | armourLayout |
P93507
|
FINISHED |
| Object | lightly armoured open-topped fighting compartment |
—
|
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: lightly armoured open-topped fighting compartment | Statement: [Nashorn, armourLayout, lightly armoured open-topped fighting compartment]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: armourLayout Context triple: [Nashorn, armourLayout, lightly armoured open-topped fighting compartment]
-
A.
crewLayout
Indicates how crew members are arranged or distributed within a vehicle, vessel, or structure.
-
B.
controlLayout
Indicates that one entity determines or manages the spatial or structural arrangement of another entity.
-
C.
armour
Indicates that an entity provides protective covering or defense for another entity.
-
D.
layoutEngine
Indicates the rendering or layout system responsible for arranging and positioning elements within a visual or document structure.
-
E.
armorDesigner
Indicates that one entity is the designer or creator of another entity’s armor.
- 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_69d381bf3dc08190bf35a2643e4e8f22 |
completed | April 6, 2026, 9:49 a.m. |
| NER | Named-entity recognition | batch_69d4ea2de4d48190aee65b3f6ec3cc48 |
completed | April 7, 2026, 11:27 a.m. |
| PD | Predicate disambiguation | batch_69d4dfb9d3648190aaabed901f22a8c0 |
completed | April 7, 2026, 10:43 a.m. |
| PDg | Predicate description generation | batch_69d4e91de3088190ae89cbb12fb29db8 |
completed | April 7, 2026, 11:23 a.m. |
Created at: April 6, 2026, 12:12 p.m.