Triple
T29681509
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Armored forces of the Red Army |
E750962
|
entity |
| Predicate | receivedEquipmentType |
P173264
|
FINISHED |
| Object | M3 Lee medium tank |
E390840
|
NE 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: M3 Lee medium tank | Statement: [Armored forces of the Red Army, receivedEquipmentType, M3 Lee medium tank]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: receivedEquipmentType Context triple: [Armored forces of the Red Army, receivedEquipmentType, M3 Lee medium tank]
-
A.
intendedEquipmentType
Indicates that a particular piece of equipment is the planned or designated type to be used in a given context or activity.
-
B.
receiverType
Indicates the category or classification of the entity that receives something (such as a message, resource, or action) in the relationship.
-
C.
laterEquipmentType
Indicates that one equipment type occurs or is used at a later time relative to another equipment type.
-
D.
typeOfEquipmentUsed
Indicates that a particular piece or category of equipment is utilized in performing a specific action, process, or activity.
-
E.
typeOfEquipmentManaged
Indicates the specific kind or category of equipment that an entity is responsible for managing.
- F. None of above. chosen
Provenance (5 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_69f0d624d7b08190ba237d226f78d0d9 |
completed | April 28, 2026, 3:45 p.m. |
| NER | Named-entity recognition | batch_69f6b342499c8190b85009a3f0f179e4 |
completed | May 3, 2026, 2:30 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a267ec5d0a8819089c4d18d9f272d20 |
completed | June 8, 2026, 8:35 a.m. |
| PD | Predicate disambiguation | batch_69f6b14d7d508190bc7d4c89dfba4a32 |
completed | May 3, 2026, 2:22 a.m. |
| PDg | Predicate description generation | batch_69f6b2a31e008190aacef03c2ebe5787 |
completed | May 3, 2026, 2:27 a.m. |
Created at: April 28, 2026, 7:10 p.m.