Triple

T13633807
Position Surface form Disambiguated ID Type / Status
Subject Haslett, Michigan E325793 entity
Predicate hasFeature P182 FINISHED
Object Lake Lansing E947097 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: Lake Lansing | Statement: [Haslett, Michigan, hasFeature, Lake Lansing]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Lake Lansing
Context triple: [Haslett, Michigan, hasFeature, Lake Lansing]
  • A. Lake Lansing chosen
    Lake Lansing is a popular recreational lake in Ingham County, Michigan, known for boating, fishing, and its surrounding park facilities.
  • B. Kalamazoo Lake
    Kalamazoo Lake is a small inland lake in western Michigan that serves as a scenic recreational and ecological feature near the village of Douglas and the Kalamazoo River.
  • C. Lake State
    Lake State is an administrative region in northern South Sudan known for its proximity to the White Nile and its predominantly Dinka population.
  • D. Muskegon Lake
    Muskegon Lake is a freshwater coastal lake in western Michigan that connects the city of Muskegon to Lake Michigan and serves as a major recreational and industrial harbor.
  • E. Stow Lake
    Stow Lake is a man-made lake and popular recreational spot in San Francisco’s Golden Gate Park, known for its boating, walking paths, and scenic island.
  • 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_69d8076beddc8190a53156f5bea77f5e completed April 9, 2026, 8:09 p.m.
NER Named-entity recognition batch_69dbc5a490508190924ac40f1dd519d6 completed April 12, 2026, 4:17 p.m.
NED1 Entity disambiguation (via context triple) batch_69fd19259070819089bd3caf66e5af29 completed May 7, 2026, 10:58 p.m.
Created at: April 9, 2026, 9:51 p.m.