Triple

T28251751

Position	Surface form	Disambiguated ID	Type / Status
Subject	Övralid Prize	`E712327`	entity
Predicate	namedAfterResidenceOf	`P174366`	FINISHED
Object	Verner von Heidenstam’s estate Övralid Verner von Heidenstam’s estate Övralid is a historic Swedish manor and former home of the Nobel Prize–winning poet, now preserved as a museum and cultural site overlooking Lake Vättern.	`E1808951`	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: Verner von Heidenstam’s estate Övralid | Statement: [Övralid Prize, namedAfterResidenceOf, Verner von Heidenstam’s estate Övralid]

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: Verner von Heidenstam’s estate Övralid
Triple: [Övralid Prize, namedAfterResidenceOf, Verner von Heidenstam’s estate Övralid]

Generated description

Verner von Heidenstam’s estate Övralid is a historic Swedish manor and former home of the Nobel Prize–winning poet, now preserved as a museum and cultural site overlooking Lake Vättern.

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

Target predicate: namedAfterResidenceOf
Context triple: [Övralid Prize, namedAfterResidenceOf, Verner von Heidenstam’s estate Övralid]

A. inResidenceAt
Indicates that an entity lives or resides at a particular location or residence.
B. residencyAt
Indicates that an entity lives or has an established residence at a particular location or address.
C. formerResidenceOf
Indicates that a location was once the place where a person or entity lived or was based, but is no longer their current residence.
D. hostResidenceOf
Indicates that a location serves as the primary place of residence for a specified person or group.
E. residencyOf
Indicates that one entity serves as the place where another entity resides or lives.
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_69efb5207eb08190827e4c34048030b1`	completed	April 27, 2026, 7:12 p.m.
NER	Named-entity recognition	`batch_69f6c20f209081909fb9ac8f95069f04`	completed	May 3, 2026, 3:33 a.m.
NED1	Entity disambiguation (via context triple)	`batch_6a15e6d9aec481909c44c57e105f68e7`	completed	May 26, 2026, 6:30 p.m.
NEDg	Description generation	`batch_6a15ee01879c8190b5e483dcd17f93a3`	completed	May 26, 2026, 7:01 p.m.
NED2	Entity disambiguation (via description)	`batch_6a15f3f763388190af2b692764ae30b6`	completed	May 26, 2026, 7:26 p.m.
PD	Predicate disambiguation	`batch_69f6bd2415fc81908c23c311aebce66f`	completed	May 3, 2026, 3:12 a.m.
PDg	Predicate description generation	`batch_69f6c125695c81909704c67bef4ce5b2`	completed	May 3, 2026, 3:29 a.m.

Created at: April 27, 2026, 11:05 p.m.