Triple

T15541121
Position Surface form Disambiguated ID Type / Status
Subject arrest at Ormiston E370476 entity
Predicate hasLocation P40 FINISHED
Object Ormiston unclear NED1 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: Ormiston | Statement: [arrest at Ormiston, hasLocation, Ormiston]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Ormiston
Context triple: [arrest at Ormiston, hasLocation, Ormiston]
  • A. Ormiston
    Ormiston is a small rural village in East Lothian, Scotland, known historically for its agricultural heritage and early coal mining.
  • B. Ormiston
    Ormiston is a coastal suburb in Redland City, Queensland, Australia, known for its residential character and proximity to Moreton Bay.
  • C. Ormiston Park Academy
    Ormiston Park Academy is a coeducational secondary school and sixth form serving the community of Aveley in Essex, England.
  • D. Schoolhill
    Schoolhill is a central street in Aberdeen, Scotland, known for housing prominent cultural institutions such as the Aberdeen Art Gallery.
  • E. Parkmill
    Parkmill is a small rural village situated in the scenic Gower Peninsula of South Wales, known as a gateway to nearby beaches, woodlands, and walking trails.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide. chosen

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_69d85cc521a08190921fb50319dddc34 completed April 10, 2026, 2:13 a.m.
NER Named-entity recognition batch_69e04432c3808190bb5b653bf8de30c6 completed April 16, 2026, 2:06 a.m.
NED1 Entity disambiguation (via context triple) batch_69ff4556ad008190a411ccd3ef0d1e89 completed May 9, 2026, 2:31 p.m.
Created at: April 10, 2026, 4:07 a.m.