Triple

T15514749
Position Surface form Disambiguated ID Type / Status
Subject Marinette campus E368805 entity
Predicate locatedIn P40 FINISHED
Object Marinette, Wisconsin E177735 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: Marinette, Wisconsin | Statement: [Marinette campus, locatedIn, Marinette, Wisconsin]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Marinette, Wisconsin
Context triple: [Marinette campus, locatedIn, Marinette, Wisconsin]
  • A. Marinette, Wisconsin chosen
    Marinette, Wisconsin is a small industrial city in northeastern Wisconsin on the shore of Green Bay, known historically for shipbuilding and its location opposite Menominee, Michigan.
  • B. Fond du Lac, Wisconsin
    Fond du Lac, Wisconsin is a small city in east-central Wisconsin known as a regional commercial center at the southern tip of Lake Winnebago.
  • C. Washington, Wisconsin
    Washington, Wisconsin is a small town located in Eau Claire County in the western part of the U.S. state of Wisconsin.
  • D. Parkland, Wisconsin
    Parkland, Wisconsin is a small rural town located in Douglas County in the northwestern part of the state.
  • E. Hudson, Wisconsin
    Hudson, Wisconsin is a small city in western Wisconsin known as a scenic St. Croix River community with a historic downtown and popular recreational waterfront.
  • 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_69d85a1794cc8190b0b428716296e63e completed April 10, 2026, 2:01 a.m.
NER Named-entity recognition batch_69e04031e62c8190953b61207142af15 completed April 16, 2026, 1:49 a.m.
NED1 Entity disambiguation (via context triple) batch_6a0067948b308190a434cdf1d45ebef4 completed May 10, 2026, 11:10 a.m.
Created at: April 10, 2026, 4:02 a.m.