Triple

T29678660
Position Surface form Disambiguated ID Type / Status
Subject I-400-class submarine E750890 entity
Predicate hasSubclass P1244 FINISHED
Object Japanese submarine I-401
Japanese submarine I-401 was a World War II Imperial Japanese Navy aircraft-carrying submarine, among the largest of its time and designed to launch surprise air attacks far from home waters.
E1880588 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: Japanese submarine I-401 | Statement: [I-400-class submarine, hasSubclass, Japanese submarine I-401]
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: Japanese submarine I-401
Triple: [I-400-class submarine, hasSubclass, Japanese submarine I-401]
Generated description
Japanese submarine I-401 was a World War II Imperial Japanese Navy aircraft-carrying submarine, among the largest of its time and designed to launch surprise air attacks far from home waters.

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_69f6725f965c81909c66601bf11c5fdc completed May 2, 2026, 9:53 p.m.
NED1 Entity disambiguation (via context triple) batch_6a26aa6bf05081909e959260765819ff completed June 8, 2026, 11:41 a.m.
NEDg Description generation batch_6a26b1df03048190a4f7a47e2d8a9899 completed June 8, 2026, 12:13 p.m.
NED2 Entity disambiguation (via description) batch_6a26b288476881908606464ce14bb779 completed June 8, 2026, 12:16 p.m.
Created at: April 28, 2026, 7:08 p.m.