Triple

T35661794

Position	Surface form	Disambiguated ID	Type / Status
Subject	JapaneseHonorificTitles	`E1030452`	entity
Predicate	includesVerbRegister	`P19921`	FINISHED
Object	Sonkeigo Sonkeigo is the highly respectful form of Japanese honorific speech used to elevate the status of the listener or the person being spoken about.	`E2150558`	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: Sonkeigo | Statement: [JapaneseHonorificTitles, includesVerbRegister, Sonkeigo]

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: Sonkeigo
Triple: [JapaneseHonorificTitles, includesVerbRegister, Sonkeigo]

Generated description

Sonkeigo is the highly respectful form of Japanese honorific speech used to elevate the status of the listener or the person being spoken about.

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

Target predicate: includesVerbRegister
Context triple: [JapaneseHonorificTitles, includesVerbRegister, Sonkeigo]

A. hasVerbClass
Indicates that an action or event is categorized into a specific verb class based on its grammatical or semantic behavior.
B. hasVerbSystemFrom
Indicates that one language or linguistic system derives or adopts its verb system from another source language or system.
C. associatedWithVerb
Indicates that one entity is connected or linked to another through some verb-based relationship or action.
D. hasComponentVerb
Indicates that an expression or construction includes a specific verb as one of its constituent components.
E. linguisticRegister chosen
Indicates the level of formality or stylistic variety in which a linguistic expression is typically used within a given context.
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_69f76e09f87881909c954aaac176c34f`	completed	May 3, 2026, 3:47 p.m.
NER	Named-entity recognition	`batch_6a037c8d06cc8190ab6a5e18d9d2571e`	completed	May 12, 2026, 7:16 p.m.
NED1	Entity disambiguation (via context triple)	`batch_6a38686511748190a38290364fa484a7`	completed	June 21, 2026, 10:40 p.m.
NEDg	Description generation	`batch_6a386957440c8190bd915a724bbb08ac`	completed	June 21, 2026, 10:44 p.m.
NED2	Entity disambiguation (via description)	`batch_6a386d862ec88190b40655d39c07c623`	completed	June 21, 2026, 11:02 p.m.
PD	Predicate disambiguation	`batch_6a037a04d8348190a4819666eab42c9b`	completed	May 12, 2026, 7:05 p.m.

Created at: May 3, 2026, 4:05 p.m.