Triple

T16669318
Position Surface form Disambiguated ID Type / Status
Subject Yattendon Court E405064 entity
Predicate isPartOf P10 FINISHED
Object Yattendon estate E405064 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: Yattendon estate | Statement: [Yattendon Court, isPartOf, Yattendon estate]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Yattendon estate
Context triple: [Yattendon Court, isPartOf, Yattendon estate]
  • A. Yattendon Court chosen
    Yattendon Court is a historic country house and estate located in the village of Yattendon in Berkshire, England.
  • B. Gurnos Estate
    Gurnos Estate is a residential area in the Swansea Valley of Wales, known primarily as a housing estate near the town of Ystradgynlais.
  • C. Donithorne estate
    Donithorne estate is the large rural property and ancestral seat associated with the Donnithorne family in George Eliot’s novel "Adam Bede."
  • D. Shottesbrooke estate
    Shottesbrooke estate is a historic English country estate centered around Shottesbrooke Park and its medieval church in Berkshire.
  • E. Houghton Estate
    Houghton Estate is an affluent, historically significant suburb of Johannesburg, South Africa, known for its large homes, tree-lined streets, and association with prominent political and business figures.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (3 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_69d8838b5fbc81908c6575c132b82e80 completed April 10, 2026, 4:58 a.m.
NER Named-entity recognition batch_69e37c9fa3d081909457b1bdea1d96e0 completed April 18, 2026, 12:44 p.m.
NED1 Entity disambiguation (via context triple) batch_6a008a34852c81908c00ff8e36923cee completed May 10, 2026, 1:37 p.m.
Created at: April 10, 2026, 5:18 a.m.