Triple

T2691518
Position Surface form Disambiguated ID Type / Status
Subject Newhaven E58411 entity
Predicate locatedNear P294 FINISHED
Object Granton E55248 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: Granton | Statement: [Newhaven, locatedNear, Granton]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Granton
Context triple: [Newhaven, locatedNear, Granton]
  • A. Granton chosen
    Granton is a coastal district in the north of Edinburgh, Scotland, historically associated with its harbour and maritime industry.
  • B. Lake City
    Lake City is a small historic mountain town in Colorado known for its scenic alpine setting, outdoor recreation, and preserved 19th-century character.
  • C. Brainerd
    Brainerd is a small city in central Minnesota, United States, known as a regional hub for outdoor recreation in the lakes area.
  • D. Grant City
    Grant City is a residential neighborhood on Staten Island, New York City, known for its suburban character and convenient access to Manhattan via the Staten Island Railway.
  • E. Paynesville
    Paynesville is a major city in Liberia, located near the capital Monrovia and known for its role as a key urban and sporting center in the country.
  • 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_69ab4ac269e481909cb317d79e68b75b completed March 6, 2026, 9:44 p.m.
NER Named-entity recognition batch_69abda0cb9b48190ab354c277cef9e23 completed March 7, 2026, 7:55 a.m.
NED1 Entity disambiguation (via context triple) batch_69afb67c04a88190bc1145397a5c4eee completed March 10, 2026, 6:13 a.m.
Created at: March 6, 2026, 9:54 p.m.