Triple

T28254787
Position Surface form Disambiguated ID Type / Status
Subject IS-2 heavy tank E712411 entity
Predicate developedFrom P1245 FINISHED
Object IS-1 heavy tank
The IS-1 heavy tank was an early World War II Soviet heavy tank that introduced the IS series design, combining strong armor and mobility as a successor to the KV line.
 E1807967 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: IS-1 heavy tank | Statement: [IS-2 heavy tank, developedFrom, IS-1 heavy tank]
NEDg Description generation gpt-5.1
Instruction
Generate a one-sentence description of the target entity. 
You are given a context triple in the form (subject, predicate, object), where the object is the target entity. 
# Instructions
Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. 
Avoid repeating the information from the triple, unless really essential.
# Response Format
Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: IS-1 heavy tank
Triple: [IS-2 heavy tank, developedFrom, IS-1 heavy tank]
Generated description
The IS-1 heavy tank was an early World War II Soviet heavy tank that introduced the IS series design, combining strong armor and mobility as a successor to the KV line.

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_69efb5207eb08190827e4c34048030b1 completed April 27, 2026, 7:12 p.m.
NER Named-entity recognition batch_69f643f3ab4081908beda310c0535ecb completed May 2, 2026, 6:35 p.m.
NED1 Entity disambiguation (via context triple) batch_6a15e6db92c08190a6d094e89418e840 completed May 26, 2026, 6:30 p.m.
NEDg Description generation batch_6a15e7bb09908190bc50b989c92a75c1 completed May 26, 2026, 6:34 p.m.
NED2 Entity disambiguation (via description) batch_6a15ec8ad948819093d9b839a1a62d00 completed May 26, 2026, 6:55 p.m.
Created at: April 27, 2026, 11:07 p.m.