Triple

T3686916
Position Surface form Disambiguated ID Type / Status
Subject Calumet Region E78246 entity
Predicate hasPart P35 FINISHED
Object Burns Harbor E194323 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: Burns Harbor | Statement: [Calumet Region, hasPart, Burns Harbor]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Burns Harbor
Context triple: [Calumet Region, hasPart, Burns Harbor]
  • A. Burns Harbor, Indiana chosen
    Burns Harbor, Indiana is a small industrial town on the shore of Lake Michigan known for its steel production facilities and proximity to the Indiana Dunes.
  • B. Indiana Harbor
    Indiana Harbor is a major industrial port district on Lake Michigan in East Chicago, Indiana, known for its steel mills and heavy manufacturing facilities.
  • C. Calumet Harbor
    Calumet Harbor is a commercial and industrial harbor on the southwest shore of Lake Michigan that serves as a key shipping and transportation hub for the Chicago region.
  • D. Huntington Harbor
    Huntington Harbor is a sheltered waterfront area and marina district on Long Island’s north shore, known for recreational boating and scenic coastal views.
  • E. Detroit Harbor
    Detroit Harbor is a sheltered natural harbor and ferry port on Washington Island in Door County, Wisconsin, serving as a key access point between the island and mainland.
  • 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_69ad85e285a081908f8cbfa9e2ed9b75 completed March 8, 2026, 2:21 p.m.
NER Named-entity recognition batch_69adc4c7e2bc81909356c8b0ed90feed completed March 8, 2026, 6:49 p.m.
NED1 Entity disambiguation (via context triple) batch_69b4cdeb6c288190a52e81fcbeaeec6d completed March 14, 2026, 2:54 a.m.
Created at: March 8, 2026, 3:26 p.m.