Triple

T16388458
Position Surface form Disambiguated ID Type / Status
Subject Ranulf le Meschin E397984 entity
Predicate residence P75 FINISHED
Object Cumberland E53833 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: Cumberland | Statement: [Ranulf le Meschin, residence, Cumberland]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Cumberland
Context triple: [Ranulf le Meschin, residence, Cumberland]
  • A. Cumberland
    Cumberland is a small town that forms part of the suburban communities within the Indianapolis metropolitan area in Indiana.
  • B. Cumberland
    Cumberland is a historic city in western Maryland known as a key transportation hub and gateway to the Appalachian Mountains and regional rail-trail networks.
  • C. Cumberland chosen
    Cumberland is a historic county in northwestern England, bordering Scotland and encompassing part of the Lake District.
  • D. Cumberland
    Cumberland is a local government area in Western Sydney, Australia, encompassing a mix of residential, commercial, and industrial suburbs.
  • E. Cumberland
    Cumberland is a suburban town in northeastern Rhode Island known for its residential communities, historic mill villages, and proximity to Providence.
  • 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_69d87f2880b48190ae1a9673a3bbef80 completed April 10, 2026, 4:40 a.m.
NER Named-entity recognition batch_69e3263f18988190800b921381d60c1b completed April 18, 2026, 6:35 a.m.
NED1 Entity disambiguation (via context triple) batch_6a003c58280081908e4d73a75b09dbb8 completed May 10, 2026, 8:05 a.m.
Created at: April 10, 2026, 5:08 a.m.