Triple
T17290680
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | SMK heavy tank prototype |
E419774
|
entity |
| Predicate | chassisRelatedTo |
P7999
|
FINISHED |
| Object | KV-1 chassis |
—
|
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: KV-1 chassis | Statement: [SMK heavy tank prototype, chassisRelatedTo, KV-1 chassis]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: chassisRelatedTo Context triple: [SMK heavy tank prototype, chassisRelatedTo, KV-1 chassis]
-
A.
chassis
chosen
Indicates that one entity serves as the structural frame or supporting base (chassis) for another entity.
-
B.
chassisOrigin
Indicates the place or source from which a chassis was originally produced, manufactured, or derived.
-
C.
chassisFeature
Indicates that a particular feature, component, or characteristic is part of or associated with a chassis.
-
D.
chassisSupplier
Indicates that one entity serves as the supplier or provider of the chassis for another entity.
-
E.
chassisName
Indicates the designated name or identifier assigned to a chassis in a system or dataset.
- F. None of above.
Provenance (3 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_69d886db32608190a61e18862c5a8af6 |
completed | April 10, 2026, 5:12 a.m. |
| NER | Named-entity recognition | batch_69e437837d048190949b947f5437636d |
completed | April 19, 2026, 2:01 a.m. |
| PD | Predicate disambiguation | batch_69e3b0118ad08190b119cd219c68ba67 |
completed | April 18, 2026, 4:23 p.m. |
Created at: April 10, 2026, 5:40 a.m.