Triple

T20257632
Position Surface form Disambiguated ID Type / Status
Subject Fort Dupont E498745 entity
Predicate borderedBy P224 FINISHED
Object Fort Davis 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: Fort Davis | Statement: [Fort Dupont, borderedBy, Fort Davis]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Fort Davis
Context triple: [Fort Dupont, borderedBy, Fort Davis]
  • A. Fort Davis
    Fort Davis was a former U.S. Army military post in the Panama Canal Zone that played a key role in the defense and operation of the Panama Canal.
  • B. Fort Davis
    Fort Davis is a small historic town in the Davis Mountains of far West Texas, known for its well-preserved frontier military post and scenic high-desert landscapes.
  • C. Fort Davis chosen
    Fort Davis is a historic Civil War–era fortification site in Washington, D.C., now preserved as part of the National Park Service’s Fort Circle Parks system.
  • D. Fort Wise
    Fort Wise was a 19th-century U.S. Army post in what is now Colorado, historically notable as the site where the controversial Treaty of Fort Wise was signed with several Plains tribes.
  • E. Sierra Blanca
    Sierra Blanca is a mountain range in southern Spain that forms part of the coastal mountains near Marbella in Andalusia.
  • 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_69da6275fa6c8190952924930adee150 completed April 11, 2026, 3:02 p.m.
NER Named-entity recognition batch_69e674c7296c819092860942de8f28d5 completed April 20, 2026, 6:47 p.m.
Created at: April 11, 2026, 11:41 p.m.