Triple

T35594546
Position Surface form Disambiguated ID Type / Status
Subject Louise Marie Thérèse d’Artois E1028591 entity
Predicate positionHeld P8 FINISHED
Object Duchess of Guastalla
The Duchess of Guastalla was a noble title associated with the small Italian principality of Guastalla, historically held by members of European royal and aristocratic families.
E128783 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: Duchess of Guastalla | Statement: [Louise Marie Thérèse d’Artois, positionHeld, Duchess of Guastalla]
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: Duchess of Guastalla
Triple: [Louise Marie Thérèse d’Artois, positionHeld, Duchess of Guastalla]
Generated description
The Duchess of Guastalla was a noble title associated with the small Italian principality of Guastalla, historically held by members of European royal and aristocratic families.

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_69f76e0598dc8190a6a093e904b9aa70 completed May 3, 2026, 3:47 p.m.
NER Named-entity recognition batch_69f79ea6f610819093d5472bef6d5106 completed May 3, 2026, 7:14 p.m.
NED1 Entity disambiguation (via context triple) batch_6a397d621de881909db1283262bc08c1 completed June 22, 2026, 6:22 p.m.
NEDg Description generation batch_6a397e4b0de88190a0531d0981ee7d97 completed June 22, 2026, 6:26 p.m.
NED2 Entity disambiguation (via description) batch_6a397edf703c81908156cbf3d2a05e01 completed June 22, 2026, 6:28 p.m.
Created at: May 3, 2026, 4:05 p.m.