Triple

T24779416

Position	Surface form	Disambiguated ID	Type / Status
Subject	Hardknott Roman Fort	`E619949`	entity
Predicate	originalLatinName	`P97178`	FINISHED
Object	Mediobogdum Mediobogdum is the Latin name of the remote Roman fort at Hardknott Pass in Cumbria, England, which guarded a key route through the western Lake District.	`E1652266`	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: Mediobogdum | Statement: [Hardknott Roman Fort, originalLatinName, Mediobogdum]

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: Mediobogdum
Triple: [Hardknott Roman Fort, originalLatinName, Mediobogdum]

Generated description

Mediobogdum is the Latin name of the remote Roman fort at Hardknott Pass in Cumbria, England, which guarded a key route through the western Lake District.

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

Target predicate: originalLatinName
Context triple: [Hardknott Roman Fort, originalLatinName, Mediobogdum]

A. hasLatinName
Indicates that an entity is associated with a specific Latin (scientific) name.
B. originalBinomialName
Indicates that one entity is the original scientific (binomial) name that was first formally assigned to the other entity (typically a species or taxon).
C. IAULatinName
Indicates that an entity has the official Latin name assigned or recognized by the International Astronomical Union (IAU).
D. historicalNameInLatin chosen
Indicates that an entity has a historically used name expressed in Latin.
E. hasOfficialNameInLatin
Indicates that an entity has an official or formally recognized name expressed in the Latin language.
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_69e2fabdbe8c8190adbb9434b8636cad`	completed	April 18, 2026, 3:30 a.m.
NER	Named-entity recognition	`batch_69f606c79ad081908369605f72e65ca6`	completed	May 2, 2026, 2:14 p.m.
NED1	Entity disambiguation (via context triple)	`batch_6a101c1f6e348190bc924bb8c65c46af`	completed	May 22, 2026, 9:04 a.m.
NEDg	Description generation	`batch_6a10273b405c8190b9a68a74c92b9e7b`	completed	May 22, 2026, 9:51 a.m.
NED2	Entity disambiguation (via description)	`batch_6a1027f5bdd4819081cf55a1ad77b4ab`	completed	May 22, 2026, 9:55 a.m.
PD	Predicate disambiguation	`batch_69f602ce79ec8190b8336c2b9de18ac7`	completed	May 2, 2026, 1:57 p.m.

Created at: April 18, 2026, 4:43 a.m.