Triple

T13397747
Position Surface form Disambiguated ID Type / Status
Subject Gunnersbury Park Mansion E319742 entity
Predicate near P350 FINISHED
Object Acton E394114 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: Acton | Statement: [Gunnersbury Park Mansion, near, Acton]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Acton
Context triple: [Gunnersbury Park Mansion, near, Acton]
  • A. Acton
    Acton is a suburban town in Middlesex County, Massachusetts, known for its residential communities, conservation land, and commuter access to Boston.
  • B. Acton
    Acton is a village and civil parish located in the county of Suffolk in eastern England.
  • C. Acton chosen
    Acton is a largely residential and commercial district in the London Borough of Ealing, known for its diverse community and good transport links into central London.
  • D. Acton
    Acton is a small community within the town of Halton Hills in Ontario, Canada, historically known for its leather and tanning industry.
  • E. Acton
    Acton is an English surname most famously associated with Lord Acton, the 19th-century historian and moralist known for the dictum "Power tends to corrupt, and absolute power corrupts absolutely."
  • 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_69d806b943cc8190b6af624d385d7e12 completed April 9, 2026, 8:06 p.m.
NER Named-entity recognition batch_69dba0d9e7348190844e11dd6cbd13b0 completed April 12, 2026, 1:40 p.m.
NED1 Entity disambiguation (via context triple) batch_69f75d84d19081909f564c90b50fda60 completed May 3, 2026, 2:36 p.m.
Created at: April 9, 2026, 9:34 p.m.