Triple

T15509627
Position Surface form Disambiguated ID Type / Status
Subject Egg Harbor Township E368670 entity
Predicate contains P35 FINISHED
Object Steelmanville E981498 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: Steelmanville | Statement: [Egg Harbor Township, contains, Steelmanville]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Steelmanville
Context triple: [Egg Harbor Township, contains, Steelmanville]
  • A. Lastoursville
    Lastoursville is a town in central Gabon known as a regional hub along the Trans-Gabon Railway and for its nearby cave systems and karst landscapes.
  • B. Steelmantown chosen
    Steelmantown is a small unincorporated community located within Upper Township in Cape May County, New Jersey.
  • C. Westerleigh
    Westerleigh is a village and civil parish in South Gloucestershire, England, known for its rural character and proximity to Bristol.
  • D. Westerleigh
    Westerleigh is a primarily residential neighborhood on Staten Island in New York City, known for its suburban character and tree-lined streets.
  • E. Cowansville
    Cowansville is a locality that serves as one of the constituent subdivisions within the municipality of Vaux-sur-Sûre in Belgium.
  • 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_69e03fd008708190a3657863eb9ac626 completed April 16, 2026, 1:48 a.m.
NED1 Entity disambiguation (via context triple) batch_69ff36702ebc81908d6a00243865de61 completed May 9, 2026, 1:28 p.m.
Created at: April 10, 2026, 3:55 a.m.