Triple

T8462062
Position Surface form Disambiguated ID Type / Status
Subject Rochester Bridge E200064 entity
Predicate connects P390 FINISHED
Object Strood E212148 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: Strood | Statement: [Rochester Bridge, connects, Strood]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Strood
Context triple: [Rochester Bridge, connects, Strood]
  • A. Strood chosen
    Strood is a town in the unitary authority of Medway in Kent, England, situated on the River Medway opposite Rochester and forming part of the Medway Towns conurbation.
  • B. Wetstraat
    Wetstraat is a major thoroughfare in Brussels that serves as a central hub for Belgian federal institutions and key European Union buildings.
  • C. Strandvliet
    Strandvliet is a metro station in Amsterdam that serves passengers on the city's rapid transit network.
  • D. Zeestraet
    Zeestraet is a notable poem by Dutch Golden Age poet Constantijn Huygens, often recognized for its vivid maritime imagery and refined Baroque style.
  • E. De Cocksdorp
    De Cocksdorp is a small village on the northern tip of the Dutch Wadden Island of Texel, known for its lighthouse and coastal landscapes.
  • 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_69ca83198c4c8190a337bf717d1813f5 completed March 30, 2026, 2:05 p.m.
NER Named-entity recognition batch_69cbe4a251f08190840a7fc31ff528b5 completed March 31, 2026, 3:13 p.m.
NED1 Entity disambiguation (via context triple) batch_69ce1df5d76881909ea5040824985cc3 completed April 2, 2026, 7:42 a.m.
Created at: March 30, 2026, 6:10 p.m.