Triple

T15220018
Position Surface form Disambiguated ID Type / Status
Subject Brookhaven, Pennsylvania E363740 entity
Predicate adjacentTo P224 FINISHED
Object Parkside, Pennsylvania E386903 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: Parkside, Pennsylvania | Statement: [Brookhaven, Pennsylvania, adjacentTo, Parkside, Pennsylvania]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Parkside, Pennsylvania
Context triple: [Brookhaven, Pennsylvania, adjacentTo, Parkside, Pennsylvania]
  • A. Parkside, Pennsylvania chosen
    Parkside, Pennsylvania is a small residential borough located in Delaware County, just outside Philadelphia.
  • B. Hyde Park, Pennsylvania
    Hyde Park, Pennsylvania is a small borough in Westmoreland County situated within the Ligonier Valley region.
  • C. Southview, Pennsylvania
    Southview, Pennsylvania is a small unincorporated community located within Cecil Township in Washington County, in the southwestern part of the state.
  • D. Mount Pleasant, Pennsylvania
    Mount Pleasant, Pennsylvania is a small borough in Westmoreland County known historically for its coal mining and glass manufacturing industries.
  • E. Parkesburg, Pennsylvania
    Parkesburg, Pennsylvania is a small borough in Chester County known historically as a railroad town along major east–west rail lines in southeastern Pennsylvania.
  • 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_69d85a0ce24c81909c4d3b6475548c95 completed April 10, 2026, 2:01 a.m.
NER Named-entity recognition batch_69e007709d3881908384f0fe1e0218d0 completed April 15, 2026, 9:47 p.m.
NED1 Entity disambiguation (via context triple) batch_69ff219294d48190a4b6754aa107b155 completed May 9, 2026, 11:59 a.m.
Created at: April 10, 2026, 3:11 a.m.