Triple

T34115365

Position	Surface form	Disambiguated ID	Type / Status
Subject	Ferdinand of Castile, Lord of Ledesma	`E874955`	entity
Predicate	lordshipOver	`P47636`	FINISHED
Object	Ledesma Ledesma is a historic town in western Spain’s Castile and León region, notable for its medieval heritage and former status as a noble lordship.	`E2083332`	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: Ledesma | Statement: [Ferdinand of Castile, Lord of Ledesma, lordshipOver, Ledesma]

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: Ledesma
Triple: [Ferdinand of Castile, Lord of Ledesma, lordshipOver, Ledesma]

Generated description

Ledesma is a historic town in western Spain’s Castile and León region, notable for its medieval heritage and former status as a noble lordship.

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

Target predicate: lordshipOver
Context triple: [Ferdinand of Castile, Lord of Ledesma, lordshipOver, Ledesma]

A. lordshipType
Indicates the specific kind or category of lordship relationship that exists between one entity and another.
B. lordshipCreated
Indicates that a lordship was formally established or brought into existence.
C. lordOf chosen
Indicates that one entity holds lordship, authority, or dominion over another entity.
D. grantedFiefOf
Indicates that one party has been formally given control or ownership of a fief (landed estate) by another authority.
E. earldomHeldBy
Indicates that a specified earldom is or was held as a title by a particular person or 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_69f349a9271c81909576994c9ef7b179`	completed	April 30, 2026, 12:23 p.m.
NER	Named-entity recognition	`batch_69f70cb880008190bc1ca79d89580949`	completed	May 3, 2026, 8:52 a.m.
NED1	Entity disambiguation (via context triple)	`batch_6a36b76d410881908099c41b5530d4ef`	completed	June 20, 2026, 3:53 p.m.
NEDg	Description generation	`batch_6a36bb3f607c8190a3f49cbcbd3e1eed`	completed	June 20, 2026, 4:09 p.m.
NED2	Entity disambiguation (via description)	`batch_6a36bd4560a081908ff4f8379d8d071d`	completed	June 20, 2026, 4:18 p.m.
PD	Predicate disambiguation	`batch_69f70ac0170c819098e3b8e41d02efef`	completed	May 3, 2026, 8:43 a.m.

Created at: May 1, 2026, 1:53 a.m.