Triple

T15815811
Position Surface form Disambiguated ID Type / Status
Subject Porte des Morts Passage E383473 entity
Predicate near P350 FINISHED
Object Rock Island E377269 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: Rock Island | Statement: [Porte des Morts Passage, near, Rock Island]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Rock Island
Context triple: [Porte des Morts Passage, near, Rock Island]
  • A. Rock Island
    Rock Island is a small city in central Washington State located along the Columbia River in Douglas County.
  • B. Rock Island chosen
    Rock Island is a small, remote island in Lake Michigan known for its state park, historic lighthouse, and rustic natural setting accessible only by boat.
  • C. Rock Island, Illinois
    Rock Island, Illinois is a historic Mississippi River city in western Illinois known as part of the Quad Cities and for its long-standing industrial and transportation significance.
  • D. Argonne
    Argonne is a forested region in northeastern France known for its rugged terrain and significant battles during World War I.
  • E. Iller
    The Iller is a river in southern Germany that flows through Bavaria and Baden-Württemberg before joining the Danube.
  • 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_69d86da2858c819090cc8481e7207b6e completed April 10, 2026, 3:25 a.m.
NER Named-entity recognition batch_69e0c4a219508190b8588120ec415ac7 completed April 16, 2026, 11:14 a.m.
NED1 Entity disambiguation (via context triple) batch_69ff99959f048190ae24a072387ec233 completed May 9, 2026, 8:31 p.m.
Created at: April 10, 2026, 4:49 a.m.