Triple

T34380266
Position Surface form Disambiguated ID Type / Status
Subject Princess Ileana of Romania E882415 entity
Predicate residence P75 FINISHED
Object Sonnberg Castle, Austria
Sonnberg Castle in Austria is a historic castle best known in modern times as the former residence of Princess Ileana of Romania.
E2093745 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: Sonnberg Castle, Austria | Statement: [Princess Ileana of Romania, residence, Sonnberg Castle, Austria]
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: Sonnberg Castle, Austria
Triple: [Princess Ileana of Romania, residence, Sonnberg Castle, Austria]
Generated description
Sonnberg Castle in Austria is a historic castle best known in modern times as the former residence of Princess Ileana of Romania.

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_69f349c0219881909393bbbc1edc8161 completed April 30, 2026, 12:23 p.m.
NER Named-entity recognition batch_69f7187155748190baad69f9f84c4349 completed May 3, 2026, 9:42 a.m.
NED1 Entity disambiguation (via context triple) batch_6a3704b780b08190aa13911b16cdda38 completed June 20, 2026, 9:23 p.m.
NEDg Description generation batch_6a370543b0c08190a81fe42444b9fbe6 completed June 20, 2026, 9:25 p.m.
NED2 Entity disambiguation (via description) batch_6a3705f992b4819080ee9743fab5932d completed June 20, 2026, 9:28 p.m.
Created at: May 1, 2026, 1:59 a.m.