Triple

T38065722
Position Surface form Disambiguated ID Type / Status
Subject House of Merode E950463 entity
Predicate hasSeat P3522 FINISHED
Object Castle of Serrant
The Castle of Serrant is a grand historic château in western France renowned for its well-preserved Renaissance architecture and richly furnished interiors.
E2254349 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: Castle of Serrant | Statement: [House of Merode, hasSeat, Castle of Serrant]
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: Castle of Serrant
Triple: [House of Merode, hasSeat, Castle of Serrant]
Generated description
The Castle of Serrant is a grand historic château in western France renowned for its well-preserved Renaissance architecture and richly furnished interiors.

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_69f76f01e63c819093b6012fc974f35a completed May 3, 2026, 3:51 p.m.
NER Named-entity recognition batch_69fbca387df48190838f476b6525c38a completed May 6, 2026, 11:09 p.m.
NED1 Entity disambiguation (via context triple) batch_6a415d3b7cbc81909b6c9ec621aba318 completed June 28, 2026, 5:43 p.m.
NEDg Description generation batch_6a415de6354c8190b728481c8b9b7544 completed June 28, 2026, 5:46 p.m.
NED2 Entity disambiguation (via description) batch_6a415f54846081909b862a6d8c2cc73a completed June 28, 2026, 5:52 p.m.
Created at: May 3, 2026, 4:21 p.m.