Triple

T9102928
Position Surface form Disambiguated ID Type / Status
Subject Euston estate E218401 entity
Predicate hasPart P35 FINISHED
Object Euston Hall E42247 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: Euston Hall | Statement: [Euston estate, hasPart, Euston Hall]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Euston Hall
Context triple: [Euston estate, hasPart, Euston Hall]
  • A. Euston Hall, Suffolk chosen
    Euston Hall, Suffolk is a historic country house and estate in eastern England that has long served as the ancestral seat of the Dukes of Grafton.
  • B. Edwardstone Hall
    Edwardstone Hall is a historic country house and estate located in the village of Edwardstone in Suffolk, England.
  • C. Euston estate
    Euston estate is a large historic country estate in Suffolk, England, surrounding Euston Hall and encompassing extensive parkland and agricultural land.
  • D. Curzon Hall
    Curzon Hall is a historic British-era academic building in Dhaka, Bangladesh, now a prominent science faculty complex of the University of Dhaka and a notable architectural landmark.
  • E. Langdell Hall
    Langdell Hall is the main library and iconic central building of Harvard Law School, housing one of the largest academic law collections in the world.
  • 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_69ca83db7448819090d0a5de842ef2ac completed March 30, 2026, 2:08 p.m.
NER Named-entity recognition batch_69cc9715d5188190bce68d095e10c2eb completed April 1, 2026, 3:55 a.m.
NED1 Entity disambiguation (via context triple) batch_69d0479a58c48190acd4a4af21aa01c3 completed April 3, 2026, 11:04 p.m.
Created at: March 30, 2026, 7:15 p.m.