Triple

T12892071
Position Surface form Disambiguated ID Type / Status
Subject Greenhorn Mountains E308392 entity
Predicate near P350 FINISHED
Object Spanish Peaks E92426 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: Spanish Peaks | Statement: [Greenhorn Mountains, near, Spanish Peaks]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Spanish Peaks
Context triple: [Greenhorn Mountains, near, Spanish Peaks]
  • A. Spanish Peaks chosen
    Spanish Peaks is a prominent pair of volcanic mountains in southern Colorado known for their distinctive twin summits and cultural significance as landmarks on the plains.
  • B. Picos
    Picos is a municipality in the Brazilian state of Piauí known as a regional commercial and services hub in the semi-arid Northeast.
  • C. Lima Peaks
    Lima Peaks are a group of rugged mountain summits in southwestern Montana, known for their dramatic relief and outdoor recreation opportunities within the northern Rocky Mountains.
  • D. Morros
    Morros is the surname of Boris Morros, a Russian-born American film producer and double agent involved in Cold War espionage.
  • E. Dos Cabezas Mountains
    The Dos Cabezas Mountains are a rugged mountain range in southeastern Arizona known for their twin-peaked skyline, diverse wildlife, and scenic desert landscapes.
  • 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_69d7bdf7c1f0819098102569a8d8cbf5 completed April 9, 2026, 2:55 p.m.
NER Named-entity recognition batch_69d97146d2208190be5ae26e51193b67 completed April 10, 2026, 9:53 p.m.
NED1 Entity disambiguation (via context triple) batch_69f6a55be3288190b2bc0bd197431db3 completed May 3, 2026, 1:31 a.m.
Created at: April 9, 2026, 5:39 p.m.