Triple

T34952038

Position	Surface form	Disambiguated ID	Type / Status
Subject	Jan Lucemburský	`E1008025`	entity
Predicate	dcera	`P181886`	FINISHED
Object	Markéta Lucemburská Markéta Lucemburská byla česká a lucemburská princezna z rodu Lucemburků, dcera krále Jana Lucemburského a sestra císaře Karla IV.	`E2119299`	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: Markéta Lucemburská | Statement: [Jan Lucemburský, dcera, Markéta Lucemburská]

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: Markéta Lucemburská
Triple: [Jan Lucemburský, dcera, Markéta Lucemburská]

Generated description

Markéta Lucemburská byla česká a lucemburská princezna z rodu Lucemburků, dcera krále Jana Lucemburského a sestra císaře Karla IV.

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

Target predicate: dcera
Context triple: [Jan Lucemburský, dcera, Markéta Lucemburská]

A. dio
Indicates that one entity is the god, deity, or divine figure associated with another entity.
B. dean
Indicates that an entity serves as the dean (administrative or academic head) of another entity, typically a faculty, school, or department.
C. cel
Indicates a celebration-related relationship or action, such as participating in, organizing, or being associated with a celebratory event or occasion.
D. crea
Indicates that one entity creates, produces, or brings into existence another entity.
E. caci
Indicates that one entity causes or brings about a change in the state or condition of another entity.
F. None of above. chosen

Provenance (7 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_69f76dc5d4308190b77553ee07b1ede6`	completed	May 3, 2026, 3:46 p.m.
NER	Named-entity recognition	`batch_69f782cf61948190b98185d961609554`	completed	May 3, 2026, 5:15 p.m.
NED1	Entity disambiguation (via context triple)	`batch_6a37a8c9cc308190a125bd2e412d1f6e`	completed	June 21, 2026, 9:03 a.m.
NEDg	Description generation	`batch_6a37a9a50f1c819085a8f3c03b11a415`	completed	June 21, 2026, 9:06 a.m.
NED2	Entity disambiguation (via description)	`batch_6a37ab6826d48190a95fcf8f2b40186a`	completed	June 21, 2026, 9:14 a.m.
PD	Predicate disambiguation	`batch_69f781020cc4819088c40cb8589504e4`	completed	May 3, 2026, 5:08 p.m.
PDg	Predicate description generation	`batch_69f782c848fc8190baea8c845ca9079f`	completed	May 3, 2026, 5:15 p.m.

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