Triple

T12814267
Position Surface form Disambiguated ID Type / Status
Subject Peak 9 E306349 entity
Predicate adjacentTo P224 FINISHED
Object Peak 10 E306350 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: Peak 10 | Statement: [Peak 9, adjacentTo, Peak 10]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Peak 10
Context triple: [Peak 9, adjacentTo, Peak 10]
  • A. Peak 10 chosen
    Peak 10 is an expert-focused mountain area at Breckenridge known for its steep, challenging terrain and advanced ski runs.
  • B. Peak 7
    Peak 7 is a popular intermediate-focused mountain area at Breckenridge Ski Resort in Colorado, known for its groomed blue runs and easy access via the BreckConnect Gondola.
  • C. Peak 15
    Peak 15 is an alternative historical name for Mount Everest, the world’s highest mountain above sea level in the Himalayas.
  • D. Peak 8
    Peak 8 is one of the main mountain areas at Breckenridge, featuring a central base village and a wide variety of ski terrain for all ability levels.
  • E. Light Peak
    Light Peak was the original codename for what became Thunderbolt, a high-speed hardware interface developed by Intel in collaboration with Apple for connecting peripherals to computers.
  • 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_69d7bdf46c448190b1faa55aaacb6317 completed April 9, 2026, 2:55 p.m.
NER Named-entity recognition batch_69d96e9beb30819097c256a5aab9a4c8 completed April 10, 2026, 9:41 p.m.
NED1 Entity disambiguation (via context triple) batch_69f68ecc83b88190a6f1ab0bb1ebaf76 completed May 2, 2026, 11:54 p.m.
Created at: April 9, 2026, 5:31 p.m.