Triple

T28141436

Position	Surface form	Disambiguated ID	Type / Status
Subject	Tridentum	`E714351`	entity
Predicate	laterRegionType	`P1828`	FINISHED
Object	Italia Annonaria Italia Annonaria was a late Roman administrative region in northern Italy, organized primarily to secure and manage the grain supply for Rome and the western empire.	`E1805117`	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: Italia Annonaria | Statement: [Tridentum, laterRegionType, Italia Annonaria]

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: Italia Annonaria
Triple: [Tridentum, laterRegionType, Italia Annonaria]

Generated description

Italia Annonaria was a late Roman administrative region in northern Italy, organized primarily to secure and manage the grain supply for Rome and the western empire.

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

Target predicate: laterRegionType
Context triple: [Tridentum, laterRegionType, Italia Annonaria]

A. laterAdministrativeRegion
Indicates that an entity became part of, or was replaced by, another administrative region at a later point in time.
B. laterTerritory
Indicates that one territory is a subsequent or successor territory to another in time.
C. regionType chosen
Indicates the classification or category of a region, specifying what kind of region it is (e.g., administrative, geographic, or functional).
D. regionalType
Indicates the classification of a region according to its designated type or category within a broader geographic or administrative system.
E. laterChannelRegion
Indicates that one channel region occurs or is positioned later in sequence or time relative to another channel region.
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_69efd6af156c81908f50c2cd7db0e1ef`	completed	April 27, 2026, 9:35 p.m.
NER	Named-entity recognition	`batch_69fd553d7cb881908d243e7a9f30ac85`	completed	May 8, 2026, 3:15 a.m.
NED1	Entity disambiguation (via context triple)	`batch_6a15d7a249808190a822fb949af996ea`	completed	May 26, 2026, 5:25 p.m.
NEDg	Description generation	`batch_6a15dad9fac881908a639795ac0a908b`	completed	May 26, 2026, 5:39 p.m.
NED2	Entity disambiguation (via description)	`batch_6a15db82ef1481908402a27126482289`	completed	May 26, 2026, 5:42 p.m.
PD	Predicate disambiguation	`batch_69fd514dcb1c81908333c70d7edd79c9`	completed	May 8, 2026, 2:58 a.m.

Created at: April 27, 2026, 9:53 p.m.