Triple

T24217031

Position	Surface form	Disambiguated ID	Type / Status
Subject	Judiciary of Iceland	`E601332`	entity
Predicate	hasCentralCourt	`P96846`	FINISHED
Object	Reykjavík District Court Reykjavík District Court is a primary trial court in Iceland’s capital that handles a wide range of civil and criminal cases within the country’s judicial system.	`E1624561`	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: Reykjavík District Court | Statement: [Judiciary of Iceland, hasCentralCourt, Reykjavík District Court]

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: Reykjavík District Court
Triple: [Judiciary of Iceland, hasCentralCourt, Reykjavík District Court]

Generated description

Reykjavík District Court is a primary trial court in Iceland’s capital that handles a wide range of civil and criminal cases within the country’s judicial system.

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

Target predicate: hasCentralCourt
Context triple: [Judiciary of Iceland, hasCentralCourt, Reykjavík District Court]

A. hasMainCourts
Indicates that an entity possesses or is associated with one or more primary courts used for official or main activities.
B. centreCourtName
Indicates the name assigned to the central court associated with a particular venue or event.
C. hasHeadCourt chosen
Indicates that an entity (such as an organization or jurisdiction) is associated with a primary or central court that serves as its main judicial authority.
D. isOnWimbledonBranch
Indicates that something is located on, or forms part of, the Wimbledon branch of a larger network or system.
E. hasTennisCourt
Indicates that one entity possesses, includes, or provides access to a tennis court as part of its facilities or attributes.
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_69e29537ca548190b94a37ebe1977caf`	completed	April 17, 2026, 8:16 p.m.
NER	Named-entity recognition	`batch_69f28208d87081909b32c84328b8f3ba`	completed	April 29, 2026, 10:11 p.m.
NED1	Entity disambiguation (via context triple)	`batch_6a0fbd21717c8190a43d559ab12e824d`	completed	May 22, 2026, 2:19 a.m.
NEDg	Description generation	`batch_6a0fbec907148190832159960dc4bdd6`	completed	May 22, 2026, 2:26 a.m.
NED2	Entity disambiguation (via description)	`batch_6a0fbf3cf7988190a9d766bfca4ef994`	completed	May 22, 2026, 2:28 a.m.
PD	Predicate disambiguation	`batch_69f1c448abec8190b87cbf9ed419a309`	completed	April 29, 2026, 8:41 a.m.

Created at: April 17, 2026, 11:58 p.m.