Triple

T32348897

Position	Surface form	Disambiguated ID	Type / Status
Subject	House of the Government	`E826538`	entity
Predicate	exertsAuthorityOver	`P139391`	FINISHED
Object	Moroccan provinces Moroccan provinces are the primary subnational administrative divisions of Morocco, each governed by appointed officials who implement national policies and oversee local affairs.	`E2004696`	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: Moroccan provinces | Statement: [House of the Government, exertsAuthorityOver, Moroccan provinces]

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: Moroccan provinces
Triple: [House of the Government, exertsAuthorityOver, Moroccan provinces]

Generated description

Moroccan provinces are the primary subnational administrative divisions of Morocco, each governed by appointed officials who implement national policies and oversee local affairs.

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

Target predicate: exertsAuthorityOver
Context triple: [House of the Government, exertsAuthorityOver, Moroccan provinces]

A. indicatesAuthorityOver
Indicates that one entity holds recognized power, control, or decision-making authority over another entity.
B. exertsControlOver chosen
Indicates that one entity has the power or authority to direct, influence, or determine the actions or decisions of another entity.
C. hasLegalAuthorityFrom
Indicates that one entity possesses formal legal power, rights, or authorization that originates from or is granted by another entity.
D. usesAuthorityOf
Indicates that one entity exercises power, rights, or influence derived from or on behalf of another entity’s authority.
E. hasLimitedAuthorityOver
Indicates that one entity holds a constrained or partial power to direct, control, or make decisions about another entity, but not full or unrestricted authority.
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_69f34914dfc48190a390cd0720d9e86f`	completed	April 30, 2026, 12:20 p.m.
NER	Named-entity recognition	`batch_69f6be5439b08190a297764d3384a6d1`	completed	May 3, 2026, 3:17 a.m.
NED1	Entity disambiguation (via context triple)	`batch_6a33e89f3db08190a357466a6d0604e2`	completed	June 18, 2026, 12:46 p.m.
NEDg	Description generation	`batch_6a33e9b614d48190b62b2be745f8e17b`	completed	June 18, 2026, 12:51 p.m.
NED2	Entity disambiguation (via description)	`batch_6a3448e2de8881908222afaa8aeeafed`	completed	June 18, 2026, 7:37 p.m.
PD	Predicate disambiguation	`batch_69f6ba6cef208190bc5cd43d96127004`	completed	May 3, 2026, 3:01 a.m.

Created at: May 1, 2026, 12:49 a.m.