Triple
T20855487
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | CVR(T) family |
E513467
|
entity |
| Predicate | roleOfVariant FV101 Scorpion |
P142123
|
FINISHED |
| Object | light reconnaissance tank |
—
|
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: light reconnaissance tank | Statement: [CVR(T) family, roleOfVariant FV101 Scorpion, light reconnaissance tank]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: roleOfVariant FV101 Scorpion Context triple: [CVR(T) family, roleOfVariant FV101 Scorpion, light reconnaissance tank]
-
A.
shipClassVariant
Indicates that one ship class is a variant or modified version derived from another ship class.
-
B.
isUncrewedVariantOf
Indicates that one entity is an uncrewed (unmanned) version or model derived from another, typically crewed, entity.
-
C.
isMilitaryVariantOf
Indicates that one entity is a military-specific version or adaptation of another, typically civilian or general-purpose, entity.
-
D.
rocketVariant
Indicates a specific version or configuration of a given rocket.
-
E.
specificCarrierAircraftVariant
Indicates that one aircraft variant is a specific version designed or adapted for carrier-based operations of another, more general aircraft variant.
- 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_69e0b4f5b01081909452f654d2fc3f50 |
completed | April 16, 2026, 10:07 a.m. |
| NER | Named-entity recognition | batch_69e6c3a81ac4819084a07625b8ed4ec5 |
completed | April 21, 2026, 12:24 a.m. |
| PD | Predicate disambiguation | batch_69e5c9a593f481908beb457c29f1ce73 |
completed | April 20, 2026, 6:37 a.m. |
| PDg | Predicate description generation | batch_69e5d53c4d6881909b4d0a716fa5ed4a |
completed | April 20, 2026, 7:26 a.m. |
Created at: April 16, 2026, 12:44 p.m.