Triple

T26327801

Position	Surface form	Disambiguated ID	Type / Status
Subject	King of Deheubarth	`E662302`	entity
Predicate	follows	`P134`	FINISHED
Object	King of Dyfed The King of Dyfed was the ruler of the early medieval Welsh kingdom of Dyfed in southwest Wales, known for its later incorporation into the larger realm of Deheubarth.	`E1717237`	NE FINISHED

How this triple was built (2 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: King of Dyfed | Statement: [King of Deheubarth, follows, King of Dyfed]

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: King of Dyfed
Triple: [King of Deheubarth, follows, King of Dyfed]

Generated description

The King of Dyfed was the ruler of the early medieval Welsh kingdom of Dyfed in southwest Wales, known for its later incorporation into the larger realm of Deheubarth.

Provenance (5 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_69ee812f32748190871d970c4e2a8ddf`	completed	April 26, 2026, 9:18 p.m.
NER	Named-entity recognition	`batch_69f60f65f9f48190ba299fb3e435e67a`	completed	May 2, 2026, 2:51 p.m.
NED1	Entity disambiguation (via context triple)	`batch_6a118fde44088190bff148ed91d1325e`	completed	May 23, 2026, 11:30 a.m.
NEDg	Description generation	`batch_6a119071f348819093c113dab0fcea45`	completed	May 23, 2026, 11:33 a.m.
NED2	Entity disambiguation (via description)	`batch_6a1190efe1a8819097407e675292a7e4`	completed	May 23, 2026, 11:35 a.m.

Created at: April 26, 2026, 10:32 p.m.