Triple

T38405351

Position	Surface form	Disambiguated ID	Type / Status
Subject	Japanese submarine RO-108	`E901011`	entity
Predicate	class	`P87`	FINISHED
Object	Ro-100 class The Ro-100 class was a group of small coastal submarines built for the Imperial Japanese Navy during World War II, designed primarily for short-range patrol and anti-shipping operations.	`E2268340`	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: Ro-100 class | Statement: [Japanese submarine RO-108, class, Ro-100 class]

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: Ro-100 class
Triple: [Japanese submarine RO-108, class, Ro-100 class]

Generated description

The Ro-100 class was a group of small coastal submarines built for the Imperial Japanese Navy during World War II, designed primarily for short-range patrol and anti-shipping operations.

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_69f76e6071a081909eea7a670d21420c`	completed	May 3, 2026, 3:48 p.m.
NER	Named-entity recognition	`batch_69fccd5e2ebc8190b2509db593c45c2e`	completed	May 7, 2026, 5:35 p.m.
NED1	Entity disambiguation (via context triple)	`batch_6a41b2bb05888190accef3685f0b3eea`	completed	June 28, 2026, 11:48 p.m.
NEDg	Description generation	`batch_6a41b67584c48190840b9d38b56b44d8`	completed	June 29, 2026, 12:04 a.m.
NED2	Entity disambiguation (via description)	`batch_6a41b6ff98248190a5f18ded2db2295e`	completed	June 29, 2026, 12:06 a.m.

Created at: May 3, 2026, 4:31 p.m.