Triple

T20515780
Position Surface form Disambiguated ID Type / Status
Subject English Electric E503678 entity
Predicate majorSite P2462 FINISHED
Object Preston NE NERFINISHED

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: Preston | Statement: [English Electric, majorSite, Preston]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Preston
Context triple: [English Electric, majorSite, Preston]
  • A. Preston
    Preston is a small city in Webster County, Georgia, serving as the county seat and local administrative center.
  • B. Preston chosen
    Preston is a historic industrial city in Lancashire, England, known for its role in the Industrial Revolution and its status as a major urban center in the North West.
  • C. Preston
    Preston is a locality within the Dover District of Kent, England, known as a small rural village community.
  • D. Preston
    Preston is a suburb in Melbourne, Australia, served by its own railway station on the metropolitan train network.
  • E. Preston
    Preston is a village in East Lothian, Scotland, known historically for its association with the nearby town of Prestonpans and its role in the region’s agricultural and industrial development.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 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_69e0b4b2aa788190ae9eb37c1d73b1f1 completed April 16, 2026, 10:06 a.m.
NER Named-entity recognition batch_69e69f41eee481908121e54c7bd691ca completed April 20, 2026, 9:48 p.m.
Created at: April 16, 2026, 11:36 a.m.