Triple

T3934092
Position Surface form Disambiguated ID Type / Status
Subject Melvindale, Michigan E90867 entity
Predicate partOf P40 FINISHED
Object Downriver E124079 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: Downriver | Statement: [Melvindale, Michigan, partOf, Downriver]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Downriver
Context triple: [Melvindale, Michigan, partOf, Downriver]
  • A. Downriver Detroit chosen
    Downriver Detroit is a suburban industrial and residential region south of Detroit along the Detroit River, encompassing several working-class communities.
  • B. Glass City
    Glass City is a nickname for Toledo, Ohio, reflecting its historic prominence in the glass manufacturing industry.
  • C. Glass City
    Glass City is a nickname commonly associated with Westland, likely referencing its historical or industrial ties to glass production or glass-related manufacturing.
  • D. Fairwater
    Fairwater is a residential neighbourhood within the town of Cwmbran in South Wales.
  • E. That Dam
    That Dam is an ancient, dark-stoned Buddhist stupa in central Vientiane, Laos, surrounded by local legends and considered one of the city’s most historic religious monuments.
  • 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_69aed95f26e0819094b0e71974543a19 completed March 9, 2026, 2:29 p.m.
NER Named-entity recognition batch_69aeedcab1808190bf653f29062cdddb completed March 9, 2026, 3:56 p.m.
NED1 Entity disambiguation (via context triple) batch_69b5288b7538819084936489226dd31f completed March 14, 2026, 9:21 a.m.
Created at: March 9, 2026, 3:23 p.m.