Triple

T19754522
Position Surface form Disambiguated ID Type / Status
Subject Kraken E474468 entity
Predicate hasCharacter P2308 FINISHED
Object Collingswood NE NERFINISHED

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: Collingswood | Statement: [Kraken, hasCharacter, Collingswood]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Collingswood
Context triple: [Kraken, hasCharacter, Collingswood]
  • A. Collingswood chosen
    Collingswood is a suburban borough in Camden County, New Jersey, known for its walkable downtown, historic homes, and convenient rail access to Philadelphia.
  • B. Hightstown
    Hightstown is a small borough in central New Jersey known for its historic downtown and residential community within Mercer County.
  • C. Moorestown Township
    Moorestown Township is a suburban community in southern New Jersey known for its historic downtown, affluent residential character, and proximity to Philadelphia.
  • D. Pennsauken
    Pennsauken is a suburban township in Camden County, New Jersey, located near Philadelphia and known for its residential neighborhoods and transportation links.
  • E. Peapack
    Peapack is a historic village in New Jersey whose name is associated with the borough of Peapack and Gladstone.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 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_69d8e51940a0819087bd2996f98da668 completed April 10, 2026, 11:55 a.m.
NER Named-entity recognition batch_69e6529dada081909c5b4d65247c6032 completed April 20, 2026, 4:21 p.m.
Created at: April 10, 2026, 1:48 p.m.