Triple

T37757407

Position	Surface form	Disambiguated ID	Type / Status
Subject	Usui Pass section between Yokokawa and Karuizawa	`E941153`	entity
Predicate	usedSpecialLocomotives	`P110444`	FINISHED
Object	EF63 class electric locomotives The EF63 class electric locomotives were powerful Japanese banking engines specifically designed to assist trains on the steep gradients of the Usui Pass.	`E2242540`	NE FINISHED

How this triple was built (3 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: EF63 class electric locomotives | Statement: [Usui Pass section between Yokokawa and Karuizawa, usedSpecialLocomotives, EF63 class electric locomotives]

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: EF63 class electric locomotives
Triple: [Usui Pass section between Yokokawa and Karuizawa, usedSpecialLocomotives, EF63 class electric locomotives]

Generated description

The EF63 class electric locomotives were powerful Japanese banking engines specifically designed to assist trains on the steep gradients of the Usui Pass.

PD Predicate disambiguation gpt-5-mini-2025-08-07

Target predicate: usedSpecialLocomotives
Context triple: [Usui Pass section between Yokokawa and Karuizawa, usedSpecialLocomotives, EF63 class electric locomotives]

A. usedLocomotives chosen
Indicates that an entity employed locomotives as tools, resources, or means to perform an action or fulfill a function.
B. laterLocomotiveType
Indicates that one locomotive type succeeds or comes after another in time, representing a later development or version in locomotive design.
C. usedInLocomotiveSeries
Indicates that something is employed or implemented within a particular locomotive series.
D. locomotiveWorks
Indicates a relationship where an entity is a facility or company that builds, repairs, or maintains locomotives.
E. locomotiveSeries
Indicates that one locomotive belongs to, or is classified under, a particular locomotive series or model line.
F. None of above.

Provenance (6 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_69f76ee1f3a88190834e6c8af99bccc9`	completed	May 3, 2026, 3:50 p.m.
NER	Named-entity recognition	`batch_69fbb9e8108c8190ae1c7940b1677e95`	completed	May 6, 2026, 10 p.m.
NED1	Entity disambiguation (via context triple)	`batch_6a40e07d5e248190bd44225f849b2a43`	completed	June 28, 2026, 8:51 a.m.
NEDg	Description generation	`batch_6a40e18eefc88190ba28efc92a9fc5fa`	completed	June 28, 2026, 8:55 a.m.
NED2	Entity disambiguation (via description)	`batch_6a40e5eb251881909402d2376b2317f2`	completed	June 28, 2026, 9:14 a.m.
PD	Predicate disambiguation	`batch_69fbb141605c8190b9c27d70352522db`	completed	May 6, 2026, 9:23 p.m.

Created at: May 3, 2026, 4:19 p.m.