Triple

T25221820
Position Surface form Disambiguated ID Type / Status
Subject Hugh IV, Duke of Burgundy E631984 entity
Predicate spouse P13 FINISHED
Object Beatrice of Navarre, Duchess of Burgundy
Beatrice of Navarre, Duchess of Burgundy, was a 13th-century Navarrese princess who became Duchess of Burgundy through her marriage into the influential Burgundian ducal house.
E1842032 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: Beatrice of Navarre, Duchess of Burgundy | Statement: [Hugh IV, Duke of Burgundy, spouse, Beatrice of Navarre, Duchess of Burgundy]
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: Beatrice of Navarre, Duchess of Burgundy
Triple: [Hugh IV, Duke of Burgundy, spouse, Beatrice of Navarre, Duchess of Burgundy]
Generated description
Beatrice of Navarre, Duchess of Burgundy, was a 13th-century Navarrese princess who became Duchess of Burgundy through her marriage into the influential Burgundian ducal house.

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_69e75a8e0f688190a7aebe9a4815e25b completed April 21, 2026, 11:07 a.m.
NER Named-entity recognition batch_69f47cc0578881909ed1e40c09fdc38d completed May 1, 2026, 10:13 a.m.
NED1 Entity disambiguation (via context triple) batch_6a24ec0f80a88190aa6f4c69962d7359 completed June 7, 2026, 3:57 a.m.
NEDg Description generation batch_6a24f092aabc81908676a4d355891072 completed June 7, 2026, 4:16 a.m.
NED2 Entity disambiguation (via description) batch_6a24f55704a081908533c0e5d81b1bb2 completed June 7, 2026, 4:36 a.m.
Created at: April 21, 2026, 1:03 p.m.