Triple

T22200478
Position Surface form Disambiguated ID Type / Status
Subject The Old Den E548667 entity
Predicate location P40 FINISHED
Object New Cross 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: New Cross | Statement: [The Old Den, location, New Cross]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: New Cross
Context triple: [The Old Den, location, New Cross]
  • A. New Cross chosen
    New Cross is an inner-city district in southeast London known for its vibrant arts and music scene, diverse community, and proximity to Goldsmiths, University of London.
  • B. Canton Crossing
    Canton Crossing is a popular mixed-use waterfront shopping and dining development located in the Canton neighborhood of Baltimore, Maryland.
  • C. Woodyard Crossing
    Woodyard Crossing is a shopping and commercial center located in Clinton, Maryland.
  • D. Stewart Crossing
    Stewart Crossing is a small roadside community in Yukon, Canada, serving as a junction and service point for travelers along the Klondike Highway.
  • E. Coles Crossing
    Coles Crossing is a master-planned residential community located in Cypress, a suburban area northwest of Houston, Texas.
  • 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_69e11e3ecc7c8190b5f94cd8f42e9d37 completed April 16, 2026, 5:37 p.m.
NER Named-entity recognition batch_69f12aea51d48190a570cd36c106ab78 completed April 28, 2026, 9:47 p.m.
Created at: April 16, 2026, 8:36 p.m.