Triple

T26572016

Position	Surface form	Disambiguated ID	Type / Status
Subject	State of Alabama ex rel. John Patterson, Attorney General	`E666851`	entity
Predicate	relator	`P191344`	FINISHED
Object	John Patterson John Patterson was an American politician who served as Attorney General and later as Governor of Alabama in the mid-20th century.	`E1736014`	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: John Patterson | Statement: [State of Alabama ex rel. John Patterson, Attorney General, relator, John Patterson]

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: John Patterson
Triple: [State of Alabama ex rel. John Patterson, Attorney General, relator, John Patterson]

Generated description

John Patterson was an American politician who served as Attorney General and later as Governor of Alabama in the mid-20th century.

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

Target predicate: relator
Context triple: [State of Alabama ex rel. John Patterson, Attorney General, relator, John Patterson]

A. relatorGeneral
Indicates a general, non-specific relationship or association between entities that does not fall under a more specialized relation type.
B. relatorDefinition
Indicates that something provides a formal description or specification that defines the nature or meaning of a relationship.
C. representative chosen
Indicates that one entity serves as an official agent or spokesperson acting on behalf of another entity.
D. appointedRelative
Indicates that one entity has formally assigned or designated another entity, who is a relative, to a specific role, position, or responsibility.
E. subjectRelation
Indicates that one entity stands in a specified relational role or connection to another entity.
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_69ee9cfa21c081909e4e36e087debfc6`	completed	April 26, 2026, 11:17 p.m.
NER	Named-entity recognition	`batch_69fe91383a1c81909266e40c3c3ede6c`	completed	May 9, 2026, 1:43 a.m.
NED1	Entity disambiguation (via context triple)	`batch_6a11ec1af938819094f565e62560a970`	completed	May 23, 2026, 6:04 p.m.
NEDg	Description generation	`batch_6a11ed7032308190bd06ce7f4ee31a7f`	completed	May 23, 2026, 6:09 p.m.
NED2	Entity disambiguation (via description)	`batch_6a11f129a14c8190873d62432560e0c4`	completed	May 23, 2026, 6:25 p.m.
PD	Predicate disambiguation	`batch_69fe8fde094081908f0f121664fbb5c7`	completed	May 9, 2026, 1:37 a.m.

Created at: April 27, 2026, 1:58 a.m.