Triple

T17481794
Position Surface form Disambiguated ID Type / Status
Subject Inverness to Elgin E425677 entity
Predicate connectsTown P845 FINISHED
Object Elgin 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: Elgin | Statement: [Inverness to Elgin, connectsTown, Elgin]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Elgin
Context triple: [Inverness to Elgin, connectsTown, Elgin]
  • A. Elgin chosen
    Elgin is a historic town in Moray, northeast Scotland, known for its medieval cathedral ruins and regional administrative and legal significance.
  • B. Elgin
    Elgin is one of the central street-dancing protagonists in the 2004 hip-hop dance film "You Got Served."
  • C. Elgin, Illinois
    Elgin, Illinois is a city in the northwest suburbs of Chicago known for its historic architecture, diverse population, and location along the Fox River.
  • D. Montrose
    Montrose is a residential neighborhood within the town of Wakefield in Middlesex County, Massachusetts.
  • E. Montrose
    Montrose is a suburb in the northern part of Hobart, Tasmania, known for its residential areas and proximity to the Derwent River.
  • 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_69d889dccf7481909264a1844a2e9100 completed April 10, 2026, 5:25 a.m.
NER Named-entity recognition batch_69e451bfd75481908c20bc2c1cbff593 completed April 19, 2026, 3:53 a.m.
Created at: April 10, 2026, 5:48 a.m.