Triple

T35825412
Position Surface form Disambiguated ID Type / Status
Subject Dux Legnicensis E1035627 entity
Predicate usedInChancery P62953 FINISHED
Object ducal chancery of Legnica
The ducal chancery of Legnica was the medieval administrative and documentary office serving the dukes of Legnica in Silesia, responsible for producing and managing official charters and records.
 E2156826 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: ducal chancery of Legnica | Statement: [Dux Legnicensis, usedInChancery, ducal chancery of Legnica]
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: ducal chancery of Legnica
Triple: [Dux Legnicensis, usedInChancery, ducal chancery of Legnica]
Generated description
The ducal chancery of Legnica was the medieval administrative and documentary office serving the dukes of Legnica in Silesia, responsible for producing and managing official charters and records.
PD Predicate disambiguation gpt-5-mini-2025-08-07 
Target predicate: usedInChancery
Context triple: [Dux Legnicensis, usedInChancery, ducal chancery of Legnica]
  • A. usedLanguageInChancery
    Indicates that a particular language was employed as the official medium of writing and record-keeping in a chancery or administrative office.
  • B. usedCourt
    Indicates that an entity made use of or participated in legal proceedings within a particular court.
  • C. usedByCourt
    Indicates that something (such as a document, argument, or evidence) is utilized or relied upon by a court in its judicial process.
  • D. hasChancery chosen
    Indicates that an entity possesses or is associated with a chancery, i.e., an official office or administrative body responsible for formal documents and records.
  • E. usedInCourts
    Indicates that something is employed or applied within legal court settings, such as in judicial proceedings or courtroom processes.
  • 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_69f76e185ffc8190880b3cdf51decd38 completed May 3, 2026, 3:47 p.m.
NER Named-entity recognition batch_69fee691952c8190822da83e46311d1d completed May 9, 2026, 7:47 a.m.
NED1 Entity disambiguation (via context triple) batch_6a38917d007481909f60c99aed49a4e4 completed June 22, 2026, 1:35 a.m.
NEDg Description generation batch_6a3892a60c5481908d570dc832907cbd completed June 22, 2026, 1:40 a.m.
NED2 Entity disambiguation (via description) batch_6a389318ff248190b94e729cc46e55b5 completed June 22, 2026, 1:42 a.m.
PD Predicate disambiguation batch_69fee62f285c8190a625562a9b80526e completed May 9, 2026, 7:45 a.m.
Created at: May 3, 2026, 4:06 p.m.