Triple
T9645163
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | TAM medium tank |
E233174
|
entity |
| Predicate | combatWeightClass |
P20168
|
FINISHED |
| Object | medium 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: medium tank | Statement: [TAM medium tank, combatWeightClass, medium tank]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: combatWeightClass Context triple: [TAM medium tank, combatWeightClass, medium tank]
-
A.
weightClass
Indicates the categorical grouping of an entity based on its weight range or mass classification.
-
B.
munitionWeightCategory
Indicates the classification of a munition based on its weight range or weight-related category.
-
C.
allowsWeightClasses
Indicates that one entity permits or supports the use of defined weight categories for another entity or within a given context.
-
D.
takeoffWeightClass
Indicates the classification of an aircraft or vehicle based on its weight at the time of takeoff.
-
E.
associatedVehicleWeightClass
chosen
Indicates the weight classification category that is linked or assigned to a particular vehicle.
- 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_69ca848b31648190b57aa55da20285be |
completed | March 30, 2026, 2:11 p.m. |
| NER | Named-entity recognition | batch_69cd9b7fd2308190803a196ecdc80d76 |
completed | April 1, 2026, 10:26 p.m. |
| PD | Predicate disambiguation | batch_69ccd5b0263081908cf6df3eb07d71b0 |
completed | April 1, 2026, 8:22 a.m. |
Created at: March 30, 2026, 8:12 p.m.