Triple

T13784236
Position Surface form Disambiguated ID Type / Status
Subject New Cross E331211 entity
Predicate adjacentTo P224 FINISHED
Object Deptford E156295 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: Deptford | Statement: [New Cross, adjacentTo, Deptford]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Deptford
Context triple: [New Cross, adjacentTo, Deptford]
  • A. Deptford chosen
    Deptford is a historic district in southeast London, England, known for its former royal dockyard where Sir Francis Drake was knighted aboard the Golden Hind.
  • B. Dagenham
    Dagenham is a suburban town in East London, historically known for its large Ford car plant and extensive post-war housing estates.
  • C. Croydon
    Croydon is a large town in South London, England, known as a major commercial and retail centre with extensive transport links into central London and surrounding areas.
  • D. Croydon
    Croydon is a residential suburb in Sydney, Australia, known for its heritage homes, village-style shopping strip, and proximity to the city centre.
  • E. Dartford
    Dartford is a historic market and industrial town in southeast England, situated on the River Darent and serving as a key commuter hub for London.
  • 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_69d81c58feb08190a77bca8bf7d6d20f completed April 9, 2026, 9:38 p.m.
NER Named-entity recognition batch_69de0248db988190aa43c3723af25f90 completed April 14, 2026, 9 a.m.
NED1 Entity disambiguation (via context triple) batch_69f7ce667c248190a9d0a0f1e9e228ae completed May 3, 2026, 10:38 p.m.
Created at: April 9, 2026, 10:11 p.m.